The days of raw speed being the only metric that matters are behind us. Now it’s about throughput, efficiency, and economics at scale. As AI evolves from providing one-shot answers to engaging in multi-step reasoning, the demand for inference and its underlying economics is increasing. This shift significantly boosts compute demand due to the generation of far more tokens per query. Metrics such as tokens per watt, cost per million tokens, and tokens per second per user are crucial alongside throughput. For power-limited AI factories, NVIDIA's continuous software improvements translate into higher token revenue over time, underscoring the importance of our technological advancements.
Pareto curves illustrate how NVIDIA Blackwell provides the best balance across the full spectrum of production priorities, including cost, energy efficiency, throughput, and responsiveness. Optimizing systems for a single scenario can limit deployment flexibility, leading to inefficiencies at other points on the curve. NVIDIA’s full-stack design approach ensures efficiency and value across multiple real-life production scenarios. Blackwell’s leadership stems from its extreme hardware-software co-design, embodying a full-stack architecture built for speed, efficiency, and scalability.
Learn about how Mixture of Experts Powers the Most Intelligent Frontier AI Models, Runs 10x Faster on NVIDIA Blackwell NVL72 in this blog.
| Network | Throughput | GPU | Server | GPU Version | Target Accuracy | Dataset |
|---|---|---|---|---|---|---|
| DeepSeek R1 | 420,659 tokens/sec | 72x GB300 | 72x GB300-288GB_aarch64, TensorRT | NVIDIA GB300 | 99% of FP16 (exact match 81.9132%) | mlperf_deepseek_r1 |
| 289,712 tokens/sec | 72x GB200 | 72x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99% of FP16 (exact match 81.9132%) | mlperf_deepseek_r1 | |
| 33,379 tokens/sec | 8x B200 | NVIDIA DGX B200 | NVIDIA B200 | 99% of FP16 (exact match 81.9132%) | mlperf_deepseek_r1 | |
| Llama3.1 405B | 16,104 tokens/sec | 72x GB300 | 72x GB300-288GB_aarch64, TensorRT | NVIDIA GB300 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | Subset of LongBench, LongDataCollections, Ruler, GovReport |
| 14,774 tokens/sec | 72x GB200 | 72x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| 1,660 tokens/sec | 8x B200 | Dell PowerEdge XE9685L | NVIDIA B200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| 553 tokens/sec | 8x H200 | Nebius H200 | NVIDIA H200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| Llama2 70B | 51,737 tokens/sec | 4x GB200 | 4x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | OpenOrca (max_seq_len=1024) |
| 102,909 tokens/sec | 8x B200 | ThinkSystem SR680a V3 | NVIDIA B200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | OpenOrca (max_seq_len=1024) | |
| 35,317 tokens/sec | 8x H200 | Dell PowerEdge XE9680 | NVIDIA H200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | OpenOrca (max_seq_len=1024) | |
| Llama3.1 8B | 146,960 tokens/sec | 8x B200 | ThinkSystem SR780a V3 | NVIDIA B200 | 99% of FP32 and 99.9% of FP32 (rouge1=42.9865, rouge2=20.1235, rougeL=29.9881) | CNN Dailymail (v3.0.0, max_seq_len=2048) |
| 66,037 tokens/sec | 8x H200 | HPE Cray XD670 | NVIDIA H200 | 99% of FP32 and 99.9% of FP32 (rouge1=42.9865, rouge2=20.1235, rougeL=29.9881) | CNN Dailymail (v3.0.0, max_seq_len=2048) | |
| Whisper | 22,273 samples/sec | 4x GB200 | BM.GPU.GB200.4 | NVIDIA GB200 | 99% of FP32 and 99.9% of FP32 (WER=2.0671%) | LibriSpeech |
| 45,333 samples/sec | 8x B200 | NVIDIA DGX B200 | NVIDIA B200 | 99% of FP32 and 99.9% of FP32 (WER=2.0671%) | LibriSpeech | |
| 34,451 samples/sec | 8x H200 | HPE Cray XD670 | NVIDIA H200 | 99% of FP32 and 99.9% of FP32 (WER=2.0671%) | LibriSpeech | |
| Stable Diffusion XL | 33 samples/sec | 8x B200 | NVIDIA DGX B200 | NVIDIA B200 | FID range: [23.01085758, 23.95007626] and CLIP range: [31.68631873, 31.81331801] | Subset of coco-2014 val |
| 19 samples/sec | 8x H200 | QuantaGrid D74H-7U | NVIDIA H200 | FID range: [23.01085758, 23.95007626] and CLIP range: [31.68631873, 31.81331801] | Subset of coco-2014 val | |
| RGAT | 651,230 samples/sec | 8x B200 | NVIDIA DGX B200 | NVIDIA B200 | 99% of FP32 (72.86%) | IGBH |
| RetinaNet | 14,997 samples/sec | 8x H200 | HPE Cray XD670 | NVIDIA H200 | 99% of FP32 (0.3755 mAP) | OpenImages (800x800) |
| DLRMv2 | 647,861 samples/sec | 8x H200 | QuantaGrid D74H-7U | NVIDIA H200 | 99% of FP32 and 99.9% of FP32 (AUC=80.31%) | Synthetic Multihot Criteo Dataset |
| Network | Throughput | GPU | Server | GPU Version | Target Accuracy | MLPerf Server Latency
Constraints (ms) |
Dataset |
|---|---|---|---|---|---|---|---|
| DeepSeek R1 | 209,328 tokens/sec | 72x GB300 | 72x GB300-288GB_aarch64, TensorRT | NVIDIA GB300 | 99% of FP16 (exact match 81.9132%) | TTFT/TPOT: 2000 ms/80 ms | mlperf_deepseek_r1 |
| 167,578 tokens/sec | 72x GB200 | 72x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99% of FP16 (exact match 81.9132%) | TTFT/TPOT: 2000 ms/80 ms | mlperf_deepseek_r1 | |
| 18,592 tokens/sec | 8x B200 | NVIDIA DGX B200 | NVIDIA B200 | 99% of FP16 (exact match 81.9132%) | TTFT/TPOT: 2000 ms/80 ms | mlperf_deepseek_r1 | |
| Llama3.1 405B | 12,248 tokens/sec | 72x GB300 | 72x GB300-288GB_aarch64, TensorRT | NVIDIA GB300 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 6000 ms/175 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport |
| 11,614 tokens/sec | 72x GB200 | 72x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 6000 ms/175 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| 1,280 tokens/sec | 8x B200 | Nebius B200 | NVIDIA B200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 6000 ms/175 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| 296 tokens/sec | 8x H200 | QuantaGrid D74H-7U | NVIDIA H200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 6000 ms/175 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| Llama3.1 405B Interactive | 9,921 tokens/sec | 72x GB200 | 72x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 4500 ms/80 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport |
| 771 tokens/sec | 8x B200 | Nebius B200 | NVIDIA B200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 4500 ms/80 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| 203 tokens/sec | 8x H200 | Nebius H200 | NVIDIA H200 | 99% of FP16 ((GovReport + LongDataCollections + 65 Sample from LongBench)rougeL=21.6666, (Remaining samples of the dataset)exact_match=90.1335) | TTFT/TPOT: 4500 ms/80 ms | Subset of LongBench, LongDataCollections, Ruler, GovReport | |
| Llama2 70B | 49,360 tokens/sec | 4x GB200 | 4x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 2000 ms/200 ms | OpenOrca (max_seq_len=1024) |
| 101,611 tokens/sec | 8x B200 | Nebius B200 | NVIDIA B200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 2000 ms/200 ms | OpenOrca (max_seq_len=1024) | |
| 34,194 tokens/sec | 8x H200 | ASUSTeK ESC N8 H200 | NVIDIA H200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 2000 ms/200 ms | OpenOrca (max_seq_len=1024) | |
| Llama2 70B Interactive | 29,746 tokens/sec | 4x GB200 | 4x GB200-186GB_aarch64, TensorRT | NVIDIA GB200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 450 ms/40 ms | OpenOrca (max_seq_len=1024) |
| 62,851 tokens/sec | 8x B200 | G894-SD1 | NVIDIA B200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 450 ms/40 ms | OpenOrca (max_seq_len=1024) | |
| 23,080 tokens/sec | 8x H200 | Nebius H200 | NVIDIA H200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 450 ms/40 ms | OpenOrca (max_seq_len=1024) | |
| Llama3.1 8B | 128,794 tokens/sec | 8x B200 | Dell PowerEdge XE9685L | NVIDIA B200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 2000 ms/100 ms | OpenOrca (max_seq_len=1024) |
| 64,915 tokens/sec | 8x H200 | HPE Cray XD670 | NVIDIA H200 | 99.9% of FP32 (rouge1=44.4312, rouge2=22.0352, rougeL=28.6162) | TTFT/TPOT: 2000 ms/100 ms | OpenOrca (max_seq_len=1024) | |
| Llama3.1 8B Interactive | 122,269 tokens/sec | 8x B200 | AS-4126GS-NBR-LCC | NVIDIA B200 | 99% of FP32 and 99.9% of FP32 (rouge1=42.9865, rouge2=20.1235, rougeL=29.9881) | TTFT/TPOT: 500 ms/30 ms | CNN Dailymail (v3.0.0, max_seq_len=2048) |
| 54,118 tokens/sec | 8x H200 | QuantaGrid D74H-7U | NVIDIA H200 | 99% of FP32 and 99.9% of FP32 (rouge1=42.9865, rouge2=20.1235, rougeL=29.9881) | TTFT/TPOT: 500 ms/30 ms | CNN Dailymail (v3.0.0, max_seq_len=2048) | |
| Stable Diffusion XL | 29 queries/sec | 8x B200 | Supermicro SYS-422GA-NBRT-LCC | NVIDIA B200 | FID range: [23.01085758, 23.95007626] and CLIP range: [31.68631873, 31.81331801] | 20 s | Subset of coco-2014 val |
| 18 queries/sec | 8x H200 | QuantaGrid D74H-7U | NVIDIA H200 | FID range: [23.01085758, 23.95007626] and CLIP range: [31.68631873, 31.81331801] | 20 s | Subset of coco-2014 val | |
| RetinaNet | 14,406 queries/sec | 8x H200 | ASUSTeK ESC N8 H200 | NVIDIA H200 | 99% of FP32 (0.3755 mAP) | 100 ms | OpenImages (800x800) |
| DLRMv2 | 591,162 queries/sec | 8x H200 | ASUSTeK ESC N8 H200 | NVIDIA H200 | 99% of FP32 (AUC=80.31%) | 60 ms | Synthetic Multihot Criteo Dataset |
MLPerf™ v5.1 Inference Closed: DeepSeek R1 99% of FP16, Llama3.1 405B 99% of FP16, Llama2 70B Interactive 99.9% of FP32, Llama2 70B 99.9% of FP32, Stable Diffusion XL, Whisper, RetinaNet, RGAT, DLRM 99% of FP32 accuracy target: 5.1-0007, 5.1-0009, 5.1-0026, 5.1-0028, 5.1-0046, 5.1-0049, 5.1-0060, 5.1-0061, 5.1-0062, 5.1-0069, 5.1-0070, 5.1-0071, 5.1-0072, 5.1-0073, 5.1-0075, 5.1-0077, 5.1-0079, 5.1-0086. MLPerf name and logo are trademarks. See
https://mlcommons.org/ for more information.
Llama3.1 8B Max Sequence Length = 2,048
Llama2 70B Max Sequence Length = 1,024
For MLPerf™ various scenario data, click
here
For MLPerf™ latency constraints, click
here
| Model | PP | TP | Input Length | Output Length | Throughput | GPU | Server | Precision | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3 235B A22B | 1 | 8 | 128 | 2048 | 66,057 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 128 | 4096 | 39,496 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 2048 | 128 | 7,329 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 5000 | 500 | 8,190 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 500 | 2000 | 57,117 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 1000 | 1000 | 42,391 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 1000 | 2000 | 34,105 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 2048 | 2048 | 26,854 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 235B A22B | 1 | 8 | 20000 | 2000 | 4,453 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 128 | 2048 | 37,844 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 128 | 4096 | 24,953 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 2048 | 128 | 6,251 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 5000 | 500 | 6,142 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 500 | 2000 | 27,817 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 1000 | 1000 | 25,828 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 1000 | 2000 | 22,051 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 2048 | 2048 | 17,554 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Qwen3 30B A3B | 1 | 1 | 20000 | 2000 | 2,944 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 128 | 2048 | 112,676 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 128 | 4096 | 68,170 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 2048 | 128 | 18,088 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 1000 | 1000 | 79,617 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 1000 | 2000 | 63,766 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 2048 | 2048 | 52,195 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Maverick | 1 | 8 | 20000 | 2000 | 12,678 output tokens/sec | 8x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 128 | 2048 | 14,699 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 128 | 4096 | 8,932 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 2048 | 128 | 3,137 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 5000 | 500 | 2,937 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 500 | 2000 | 11,977 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 1000 | 1000 | 10,591 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 1000 | 2000 | 9,356 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 2048 | 2048 | 7,152 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v4 Scout | 1 | 1 | 20000 | 2000 | 1,644 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 128 | 2048 | 9,922 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 128 | 4096 | 6,831 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 2048 | 128 | 1,339 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 5000 | 500 | 1,459 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 500 | 2000 | 7,762 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 1000 | 1000 | 7,007 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 1000 | 2000 | 6,737 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 0.19.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 2048 | 2048 | 4,783 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.3 70B | 1 | 1 | 20000 | 2000 | 665 output tokens/sec | 1x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 128 | 2048 | 8,020 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 128 | 4096 | 6,345 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 2048 | 128 | 749 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 5000 | 500 | 1,048 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 500 | 2000 | 6,244 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 1000 | 1000 | 5,209 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 1000 | 2000 | 4,933 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 2048 | 2048 | 4,212 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
| Llama v3.1 405B | 1 | 4 | 20000 | 2000 | 672 output tokens/sec | 4x B200 | DGX B200 | FP4 | TensorRT-LLM 1.0 | NVIDIA B200 |
TP: Tensor Parallelism
PP: Pipeline Parallelism
For more information on pipeline parallelism, please read
Llama v3.1 405B Blog
Output tokens/second on Llama v3.1 405B is inclusive of time to generate the first token (tokens/s = total generated tokens / total latency)
| Model | PP | TP | Input Length | Output Length | Throughput | GPU | Server | Precision | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|
| Llama v4 Scout | 4 | 1 | 128 | 128 | 17,857 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 128 | 2048 | 9,491 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 2 | 2 | 128 | 4096 | 6,281 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 2048 | 128 | 3,391 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 5000 | 500 | 2,496 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 500 | 2000 | 9,253 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 1000 | 1000 | 8,121 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 1000 | 2000 | 6,980 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v4 Scout | 4 | 1 | 2048 | 2048 | 4,939 output tokens/sec | 4x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 128 | 2048 | 4,776 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 128 | 4096 | 2,960 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 500 | 2000 | 4,026 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 1000 | 1000 | 3,658 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 1000 | 2000 | 3,106 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 2048 | 2048 | 2,243 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.3 70B | 2 | 1 | 20000 | 2000 | 312 output tokens/sec | 2x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 128 | 128 | 4,866 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 128 | 2048 | 3,132 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 2048 | 128 | 588 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 5000 | 500 | 616 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 500 | 2000 | 2,468 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 1000 | 1000 | 2,460 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 1000 | 2000 | 2,009 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 405B | 8 | 1 | 2048 | 2048 | 1,485 output tokens/sec | 8x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 128 | 128 | 22,757 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 128 | 4096 | 7,585 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 2048 | 128 | 2,653 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 5000 | 500 | 2,283 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 500 | 2000 | 10,612 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 1000 | 2000 | 8,000 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 2048 | 2048 | 5,423 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
| Llama v3.1 8B | 1 | 1 | 20000 | 2000 | 756 output tokens/sec | 1x RTX PRO 6000 | Supermicro SYS-521GE-TNRT | FP4 | TensorRT-LLM 0.21.0 | NVIDIA RTX PRO 6000 Blackwell Server Edition |
TP: Tensor Parallelism
PP: Pipeline Parallelism
For more information on pipeline parallelism, please read
Llama v3.1 405B Blog
Output tokens/second on Llama v3.1 405B is inclusive of time to generate the first token (tokens/s = total generated tokens / total latency)
| Model | PP | TP | Input Length | Output Length | Throughput | GPU | Server | Precision | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3 235B A22B | 1 | 8 | 128 | 2048 | 42,821 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 128 | 4096 | 26,852 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 2048 | 128 | 3,331 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 5000 | 500 | 3,623 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 500 | 2000 | 28,026 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 1000 | 1000 | 23,789 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 1000 | 2000 | 22,061 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 2048 | 2048 | 16,672 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Qwen3 235B A22B | 1 | 8 | 20000 | 2000 | 1,876 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 128 | 2048 | 40,572 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 128 | 4096 | 24,616 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 2048 | 128 | 7,307 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 5000 | 500 | 8,456 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 500 | 2000 | 37,835 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 1000 | 1000 | 31,782 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 1000 | 2000 | 34,734 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 2048 | 2048 | 20,957 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Maverick | 1 | 8 | 20000 | 2000 | 4,106 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 128 | 2048 | 34,316 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 128 | 4096 | 21,332 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 2048 | 128 | 3,699 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 5000 | 500 | 4,605 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 500 | 2000 | 24,630 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 1000 | 1000 | 21,636 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 1000 | 2000 | 18,499 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 2048 | 2048 | 14,949 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v4 Scout | 1 | 4 | 20000 | 2000 | 2,105 output tokens/sec | 4x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 128 | 2048 | 4,336 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 128 | 4096 | 2,872 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 2048 | 128 | 442 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 5000 | 500 | 566 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 500 | 2000 | 3,666 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 1000 | 1000 | 2,909 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 1000 | 2000 | 2,994 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 2048 | 2048 | 2,003 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.3 70B | 1 | 1 | 20000 | 2000 | 283 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 128 | 2048 | 5,661 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 0.19.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 128 | 4096 | 5,167 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 0.19.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 2048 | 128 | 456 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 5000 | 500 | 650 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 500 | 2000 | 4,724 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 1000 | 1000 | 3,330 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 1000 | 2000 | 3,722 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 2048 | 2048 | 2,948 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 405B | 1 | 8 | 20000 | 2000 | 505 output tokens/sec | 8x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 128 | 2048 | 26,221 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 128 | 4096 | 18,027 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 2048 | 128 | 3,538 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 5000 | 500 | 3,902 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 500 | 2000 | 20,770 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 1000 | 1000 | 17,744 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 1000 | 2000 | 16,828 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 2048 | 2048 | 12,194 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
| Llama v3.1 8B | 1 | 1 | 20000 | 2000 | 1,804 output tokens/sec | 1x H200 | DGX H200 | FP8 | TensorRT-LLM 1.0 | NVIDIA H200 |
TP: Tensor Parallelism
PP: Pipeline Parallelism
For more information on pipeline parallelism, please read
Llama v3.1 405B Blog
Output tokens/second on Llama v3.1 405B is inclusive of time to generate the first token (tokens/s = total generated tokens / total latency)
| Model | PP | TP | Input Length | Output Length | Throughput | GPU | Server | Precision | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|
| Llama v3.3 70B | 1 | 2 | 128 | 2048 | 6,651 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 128 | 4096 | 4,199 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 2048 | 128 | 762 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 5000 | 500 | 898 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 500 | 2000 | 5,222 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 1000 | 1000 | 4,205 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 1000 | 2000 | 4,146 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 2048 | 2048 | 3,082 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.3 70B | 1 | 2 | 20000 | 2000 | 437 output tokens/sec | 2x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 128 | 2048 | 4,340 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 128 | 4096 | 3,116 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 2048 | 128 | 453 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 5000 | 500 | 610 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 500 | 2000 | 3,994 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 1000 | 1000 | 2,919 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 1000 | 2000 | 2,895 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 2048 | 2048 | 2,296 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 405B | 1 | 8 | 20000 | 2000 | 345 output tokens/sec | 8x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 128 | 2048 | 22,714 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 128 | 4096 | 14,325 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 2048 | 128 | 3,450 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 5000 | 500 | 3,459 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 500 | 2000 | 17,660 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 1000 | 1000 | 15,220 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 1000 | 2000 | 13,899 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 2048 | 2048 | 9,305 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
| Llama v3.1 8B | 1 | 1 | 20000 | 2000 | 1,351 output tokens/sec | 1x H100 | DGX H100 | FP8 | TensorRT-LLM 1.0 | H100-SXM5-80GB |
TP: Tensor Parallelism
PP: Pipeline Parallelism
| Model | PP | TP | Input Length | Output Length | Throughput | GPU | Server | Precision | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|
| Llama v4 Scout | 2 | 2 | 128 | 2048 | 1,105 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 2 | 2 | 128 | 4096 | 707 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 4 | 1 | 2048 | 128 | 561 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 4 | 1 | 5000 | 500 | 307 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 2 | 2 | 500 | 2000 | 1,093 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 2 | 2 | 1000 | 1000 | 920 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 2 | 2 | 1000 | 2000 | 884 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v4 Scout | 2 | 2 | 2048 | 2048 | 615 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.3 70B | 4 | 1 | 128 | 2048 | 1,694 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.3 70B | 2 | 2 | 128 | 4096 | 972 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.3 70B | 4 | 1 | 500 | 2000 | 1,413 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.3 70B | 4 | 1 | 1000 | 1000 | 1,498 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.3 70B | 4 | 1 | 1000 | 2000 | 1,084 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.3 70B | 4 | 1 | 2048 | 2048 | 773 output tokens/sec | 4x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 128 | 128 | 8,471 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 128 | 4096 | 2,888 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 2048 | 128 | 1,017 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 5000 | 500 | 863 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 500 | 2000 | 4,032 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 1000 | 2000 | 3,134 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 2048 | 2048 | 2,148 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
| Llama v3.1 8B | 1 | 1 | 20000 | 2000 | 280 output tokens/sec | 1x L40S | Supermicro SYS-521GE-TNRT | FP8 | TensorRT-LLM 0.21.0 | NVIDIA L40S |
TP: Tensor Parallelism
PP: Pipeline Parallelism
| Network | Batch Size | Throughput | Efficiency | Latency (ms) | GPU | Server | Container | Precision | Dataset | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Stable Diffusion v2.1 (512x512) | 1 | 6.8 images/sec | - | 225.55 | 1x B200 | DGX B200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| Stable Diffusion XL | 1 | 2.85 images/sec | - | 522.86 | 1x B200 | DGX B200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| ResNet-50v1.5 | 2048 | 118,265 images/sec | 121 images/sec/watt | 17.32 | 1x B200 | DGX B200 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| BEVFusion Head | 1 | 2869.15 images/sec | 6 sequences/sec/watt | 0.35 | 1x B200 | DGX B200 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| Flux Image Generator | 1 | .48 images/sec | - sequences/sec/watt | 2079.78 | 1x B200 | DGX B200 | 25.08-py3 | FP4 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| HF Swin Base | 128 | 4,572 samples/sec | 5 samples/sec/watt | 28 | 1x B200 | DGX B200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| HF Swin Large | 128 | 2,820 samples/sec | 3 samples/sec/watt | 45.4 | 1x B200 | DGX B200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| HF ViT Base | 1024 | 8,839 samples/sec | 9 samples/sec/watt | 115.85 | 1x B200 | DGX B200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| HF ViT Large | 2048 | 3,127 samples/sec | 3 samples/sec/watt | 655.02 | 1x B200 | DGX B200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| Yolo v10 M | 1 | 849.29 sequences/sec | 1 sequences/sec/watt | 1.18 | 1x B200 | DGX B200 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
| Yolo v11 M | 1 | 1043.32 samples/sec | 1 samples/sec/watt | 0.96 | 1x B200 | DGX B200 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA B200 |
HF Swin Base: Input Image Size = 224x224 | Window Size = 224x 224. HF Swin Large: Input Image Size = 224x224 | Window Size = 384x384
HF ViT Base: Input Image Size = 224x224 | Patch Size = 224x224. HF ViT Large: Input Image Size = 224x224 | Patch Size = 384x384
| Network | Batch Size | Throughput | Efficiency | Latency (ms) | GPU | Server | Container | Precision | Dataset | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Stable Diffusion v2.1 (512x512) | 1 | 3.92 images/sec | - | 330 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| Stable Diffusion XL | 1 | 1.6 images/sec | - | 750.22 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| ResNet-50v1.5 | 2048 | 81,317 images/sec | 117 images/sec/watt | 25.19 | 1x H200 | DGX H200 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| BEVFusion Head | 1 | 2005.18 sequences/sec | 6 sequences/sec/watt | 0.5 | 1x H200 | DGX H200 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| Flux Image Generator | 1 | .21 images/sec | - | 4813.58 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| HF Swin Base | 128 | 2,976 samples/sec | 4 samples/sec/watt | 43 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| HF Swin Large | 128 | 1,803 samples/sec | 3 samples/sec/watt | 70.98 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| HF ViT Base | 2048 | 4,930 samples/sec | 7 samples/sec/watt | 415.4 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| HF ViT Large | 2048 | 1,684 samples/sec | 2 samples/sec/watt | 1215.82 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| Yolo v10 M | 1 | 432.01 images/sec | 1 images/sec/watt | 2.31 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
| Yolo v11 M | 8 | 509.23 images/sec | 1 images/sec/watt | 1.96 | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 |
HF Swin Base: Input Image Size = 224x224 | Window Size = 224x 224. HF Swin Large: Input Image Size = 224x224 | Window Size = 384x384
HF ViT Base: Input Image Size = 224x224 | Patch Size = 224x224. HF ViT Large: Input Image Size = 224x224 | Patch Size = 384x384
| Network | Batch Size | Throughput | Efficiency | Latency (ms) | GPU | Server | Container | Precision | Dataset | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|---|
| ResNet-50v1.5 | 2048 | 78,875 images/sec | 119 images/sec/watt | 25.97 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| BEVFusion Head | 1 | 2013.77 images/sec | 6 images/sec/watt | 0.5 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| Flux Image Generator | 1 | . images/sec | - | 1x H200 | DGX H200 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA H200 | |
| HF Swin Base | 128 | 2,886 samples/sec | 4 samples/sec/watt | 44.35 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| HF Swin Large | 128 | 1,733 samples/sec | 3 samples/sec/watt | 73.87 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| HF ViT Base | 2048 | 4,710 samples/sec | 7 samples/sec/watt | 434.79 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| HF ViT Large | 2048 | 1,626 samples/sec | 2 samples/sec/watt | 1259.68 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| Yolo v10 M | 1 | 433.57 images/sec | 1 images/sec/watt | 2.31 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
| Yolo v11 M | 1 | 504.17 images/sec | 1 images/sec/watt | 1.98 | 1x GH200 | NVIDIA P3880 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA GH200 |
HF Swin Base: Input Image Size = 224x224 | Window Size = 224x 224. HF Swin Large: Input Image Size = 224x224 | Window Size = 384x384
HF ViT Base: Input Image Size = 224x224 | Patch Size = 224x224. HF ViT Large: Input Image Size = 224x224 | Patch Size = 384x384
| Network | Batch Size | Throughput | Efficiency | Latency (ms) | GPU | Server | Container | Precision | Dataset | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Stable Diffusion v2.1 (512x512) | 1 | 3.83 images/sec | - | 340.56 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| Stable Diffusion XL | 1 | 1.6 images/sec | - | 774.71 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| ResNet-50v1.5 | 2048 | 75,476 images/sec | 110 images/sec/watt | 27.13 | 1x H100 | DGX H100 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| BEVFusion Head | 1 | 1998.95 images/sec | 6 images/sec/watt | 0.5 | 1x H100 | DGX H100 | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| Flux Image Generator | 1 | .21 images/sec | - | 4747.1 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| HF Swin Base | 128 | 2,852 samples/sec | 4 samples/sec/watt | 44.88 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| HF Swin Large | 128 | 1,792 samples/sec | 3 samples/sec/watt | 71.44 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| HF ViT Base | 2048 | 4,988 samples/sec | 7 samples/sec/watt | 410.58 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| HF ViT Large | 2048 | 5,418 samples/sec | 8 samples/sec/watt | 377.97 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| Yolo v10 M | 1 | 407.43 images/sec | 1 images/sec/watt | 2.45 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
| Yolo v11 M | 1 | 476 images/sec | 1 images/sec/watt | 2.1 | 1x H100 | DGX H100 | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | H100 SXM5-80GB |
HF Swin Base: Input Image Size = 224x224 | Window Size = 224x 224. HF Swin Large: Input Image Size = 224x224 | Window Size = 384x384
HF ViT Base: Input Image Size = 224x224 | Patch Size = 224x224. HF ViT Large: Input Image Size = 224x224 | Patch Size = 384x384
| Network | Batch Size | Throughput | Efficiency | Latency (ms) | GPU | Server | Container | Precision | Dataset | Framework | GPU Version |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Stable Diffusion v2.1 (512x512) | 1 | 1.65 images/sec | - | 607.21 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| Stable Diffusion XL | 1 | .6 images/sec | - | 1676.69 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| ResNet-50v1.5 | 2048 | 23,555 images/sec | 68 images/sec/watt | 86.94 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| BEVFusion Head | 1 | 1944.21 images/sec | 7 images/sec/watt | 0.51 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| HF Swin Base | 32 | 1,376 samples/sec | 4 samples/sec/watt | 23.26 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| HF Swin Large | 32 | 705 samples/sec | 2 samples/sec/watt | 45.42 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| HF ViT Base | 1024 | 1,655 samples/sec | 5 samples/sec/watt | 618.88 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| HF ViT Large | 2048 | 570 samples/sec | 2 samples/sec/watt | 3591.09 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | FP8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| Yolo v10 M | 1 | 273.25 samples/sec | 1 samples/sec/watt | 3.66 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
| Yolo v11 M | 1 | 308 images/sec | 1 images/sec/watt | 3.25 | 1x L40S | Supermicro SYS-521GE-TNRT | 25.08-py3 | INT8 | Synthetic | TensorRT 10.13.2 | NVIDIA L40S |
HF Swin Base: Input Image Size = 224x224 | Window Size = 224x 224. HF Swin Large: Input Image Size = 224x224 | Window Size = 384x384
HF ViT Base: Input Image Size = 224x224 | Patch Size = 224x224. HF ViT Large: Input Image Size = 224x224 | Patch Size = 384x384
Deploying AI in real-world applications requires training networks to convergence at a specified accuracy. This is the best methodology to test whether AI systems are ready to be deployed in the field to deliver meaningful results.
NVIDIA Riva is an application framework for multimodal conversational AI services that deliver real-performance on GPUs.