Qwen3 8B
153 records across 33 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GB300 | Qwen3 8B | unspecified | vLLM | 25781 | – | – | – | 256 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 25515 | – | – | – | 256 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 24811 | – | – | – | 256 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 23488 | – | – | – | 256 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 22873 | – | – | – | 256 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 21249 | – | – | – | 256 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 16515 | – | – | – | 1024 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 16364 | – | – | – | 1024 | 2026-10-01 | community | – | source |
| GB300 | Qwen3 8B | unspecified | vLLM | 15705 | – | – | – | 1024 | 2026-10-01 | community | – | source |
| RTX PRO 6000 Blackwell Workstation Edition | Qwen3 8B 8B dense | BF16 | vLLM | 3936.20 | – | – | – | – | 2026-04 | community | – | source |
| RTX PRO 6000 Blackwell Workstation Edition | Qwen3 8B 8B dense | BF16 | vLLM | 3841.50 | – | – | – | – | 2026-04 | community | – | source |
| RTX PRO 6000 Blackwell Workstation Edition | Qwen3 8B 8B dense | BF16 | vLLM | 3713.23 | – | – | – | – | 2026-04 | community | – | source |
| RTX PRO 6000 Blackwell Workstation Edition | Qwen3 8B 8B dense | BF16 | vLLM | 2021.33 | – | – | – | – | 2026-04 | community | – | source |
| H100 | Qwen3 8B 8B dense | FP8 | vLLM | 839.75 | – | – | – | – | 2026-07 | community | – | source |
| H100 | Qwen3 8B 8B dense | FP8 | vLLM | 809.40 | – | – | – | – | 2026-07 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 235.00 | – | – | – | tg128 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 234.35 | – | – | – | tg128 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 234.31 | – | – | – | tg128 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 215.63 | – | – | – | tg128 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 212.66 | – | – | – | 4096 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 211.93 | – | – | – | 4096 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 211.85 | – | – | – | 4096 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 171.85 | – | – | – | 16384 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 169.06 | – | – | – | 16384 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 168.94 | – | – | – | 16384 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 164.41 | – | – | – | 4096 | 2026-10 | community | – | source |
| RTX Pro 5000 Blackwell | Qwen3 8B 8B | Q4_K | llama.cpp | 159.8 | 8175.3 | – | – | 4096 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B 8B | Q4_K | llama.cpp | 141.3 | 9250.5 | – | – | 4096 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B | Q4_K_M | llama.cpp llama-bench | 141.3 | – | – | – | 4096 | 2026-08-17 | sourced | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 134.39 | – | – | – | 32768 | 2026-10 | community | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 133.9 | 4932.5 | – | – | 4096 | – | sourced | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 131.24 | – | – | – | 32768 | 2026-10 | community | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 131.09 | – | – | – | 32768 | 2026-10 | community | – | source |
| RTX 5080 | Qwen3 8B 8B | Q4_K | llama.cpp | 129.1 | 6410.1 | – | – | 4096 | – | sourced | – | source |
| RTX Pro 5000 Blackwell | Qwen3 8B 8B | Q4_K | llama.cpp | 126.3 | 5846.4 | – | – | 16384 | – | sourced | – | source |
| RTX 3090 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 123.7 | 4467.9 | – | – | 4096 | – | sourced | – | source |
| RTX 5070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 120.5 | 5557.3 | – | – | 4096 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 115.2 | 4211.7 | – | – | 4096 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B 8B | Q4_K | llama.cpp | 108.0 | 5530.5 | – | – | 16384 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B | Q4_K_M | llama.cpp llama-bench | 108 | – | – | – | 16384 | 2026-08-17 | sourced | – | source |
| M5 Max | Qwen3 8B | 4bit | oMLX | 104.7 | 3386.0 | – | – | 1024 | 2026-10-13 | community | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 104.2 | 6137.0 | – | – | 4096 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 102.7 | 6177.9 | – | – | 4096 | – | sourced | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 100.54 | – | – | – | 16384 | 2026-10 | community | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 98.7 | 4096.4 | – | – | 16384 | – | sourced | – | source |
| RTX Pro 5000 Blackwell | Qwen3 8B 8B | Q4_K | llama.cpp | 98.3 | 4006.2 | – | – | 32768 | – | sourced | – | source |
| M5 Max | Qwen3 8B | 4bit | oMLX | 98.3 | 3468.0 | – | – | 4096 | 2026-10-13 | community | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 96.3 | 5220.1 | – | – | 4096 | – | sourced | – | source |
| RTX 5080 | Qwen3 8B 8B | Q4_K | llama.cpp | 94.1 | 4024.4 | – | – | 16384 | – | sourced | – | source |
| RTX 3090 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 93.6 | 2834.2 | – | – | 16384 | – | sourced | – | source |
| RTX A6000 | Qwen3 8B 8B | Q4_K | llama.cpp | 90.5 | 2756.0 | – | – | 4096 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 87.9 | 2658.5 | – | – | 16384 | – | sourced | – | source |
| RTX 5070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 87.5 | 3653.8 | – | – | 16384 | – | sourced | – | source |
| RTX 5070 | Qwen3 8B 8B | Q4_K | llama.cpp | 85.8 | 3487.7 | – | – | 4096 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B 8B | Q4_K | llama.cpp | 82.3 | 3560.1 | – | – | 32768 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B | Q4_K_M | llama.cpp llama-bench | 82.3 | – | – | – | 32768 | 2026-08-17 | sourced | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 79.4 | 3858.1 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 77.9 | 3809.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 75.8 | 4877.7 | – | – | 4096 | – | sourced | – | source |
| RTX 4070 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 75.4 | 4321.7 | – | – | 4096 | – | sourced | – | source |
| RTX 5080 | Qwen3 8B 8B | Q4_K | llama.cpp | 72.5 | 1943.3 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 72.2 | 3050.7 | – | – | 16384 | – | sourced | – | source |
| RTX 3090 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 71.8 | 1868.0 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 | Qwen3 8B 8B | Q4_K | llama.cpp | 71.2 | 3564.1 | – | – | 4096 | – | sourced | – | source |
| RTX 5060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 69.2 | 2965.1 | – | – | 4096 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 68.9 | 2218.5 | – | – | 32768 | – | sourced | – | source |
| RTX 3080 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 68.1 | 1761.2 | – | – | 32768 | – | sourced | – | source |
| RTX 5090 | Qwen3 8B | Q4_K_M | llama.cpp (CUDA) | 65.07 | – | – | – | 32768 | 2026-10 | community | – | source |
| RTX A6000 | Qwen3 8B 8B | Q4_K | llama.cpp | 64.3 | 2428.0 | – | – | 16384 | – | sourced | – | source |
| RTX Pro 5000 Blackwell | Qwen3 8B 8B | Q4_K | llama.cpp | 64.1 | 2120.7 | – | – | 65536 | – | sourced | – | source |
| RTX 5070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 63.3 | 2269.0 | – | – | 32768 | – | sourced | – | source |
| M1 Max | Qwen3 8B | 4bit | oMLX | 60.5 | 394.8 | – | – | 1024 | 2026-10-08 | community | – | source |
| M5 Pro | Qwen3 8B | 4bit | oMLX | 60.2 | 1497.0 | – | – | 1024 | 2026-10-11 | community | – | source |
| M5 Pro | Qwen3 8B | 4bit | oMLX | 60.2 | 1497.0 | – | – | 1024 | 2026-10-11 | community | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 59.5 | 2537.1 | – | – | 32768 | – | sourced | – | source |
| RTX 5070 | Qwen3 8B 8B | Q4_K | llama.cpp | 59.1 | 1600.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 59.0 | 1968.4 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 57.6 | 2274.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4070 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 56.2 | 2525.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B 8B | Q4_K | llama.cpp | 56.1 | 2028.6 | – | – | 65536 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B | Q4_K_M | llama.cpp llama-bench | 56.1 | – | – | – | 65536 | 2026-08-17 | sourced | – | source |
| RTX 3060 12GB | Qwen3 8B 8B | Q4_K | llama.cpp | 55.2 | 1696.8 | – | – | 4096 | – | sourced | – | source |
| M5 Pro | Qwen3 8B | 4bit | oMLX | 55.1 | 1426.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M5 Pro | Qwen3 8B | 4bit | oMLX | 55.1 | 1426.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 54.5 | 1616.6 | – | – | 32768 | – | sourced | – | source |
| M1 Max | Qwen3 8B | 4bit | oMLX | 54.5 | 376.3 | – | – | 4096 | 2026-10-08 | community | – | source |
| M1 Max | Qwen3 8B | 4bit | oMLX | 54.4 | 378.3 | – | – | 4096 | 2026-10-08 | community | – | source |
| M1 Max | Qwen3 8B | 4bit | oMLX | 54.0 | 378.6 | – | – | 4096 | 2026-10-08 | community | – | source |
| RTX 4070 | Qwen3 8B 8B | Q4_K | llama.cpp | 52.1 | 2064.3 | – | – | 16384 | – | sourced | – | source |
| RTX 5060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 51.4 | 1447.9 | – | – | 16384 | – | sourced | – | source |
| M4 Pro | Qwen3 8B | 4bit | oMLX | 51.0 | 467.5 | – | – | 1024 | 2026-10-14 | community | – | source |
| RTX 3090 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 49.0 | 1111.1 | – | – | 65536 | – | sourced | – | source |
| RTX 5080 | Qwen3 8B 8B | Q4_K | llama.cpp | 49.0 | 1124.6 | – | – | 65536 | – | sourced | – | source |
| M4 Pro | Qwen3 8B | 4bit | oMLX | 46.0 | 450.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| RTX 4060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 45.8 | 2675.2 | – | – | 4096 | – | sourced | – | source |
| M4 Pro | Qwen3 8B | 4bit | oMLX | 45.7 | 355.4 | – | – | 4096 | 2026-10-13 | community | – | source |
| M4 Pro | Qwen3 8B | 4bit | oMLX | 45.6 | 448.2 | – | – | 4096 | 2026-10-14 | community | – | source |
| RTX A6000 | Qwen3 8B 8B | Q4_K | llama.cpp | 44.6 | 1593.3 | – | – | 32768 | – | sourced | – | source |
| M4 Max | Qwen3 8B | 4bit | oMLX | 44.2 | 573.6 | – | – | 16384 | 2026-10-11 | community | – | source |
| M4 Max | Qwen3 8B | 8bit | oMLX | 44.1 | 738.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| RTX 5070 | Qwen3 8B 8B | Q4_K | llama.cpp | 43.6 | 898.8 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 42.2 | 1595.7 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 42.1 | 1099.7 | – | – | 32768 | – | sourced | – | source |
| RTX 3060 12GB | Qwen3 8B 8B | Q4_K | llama.cpp | 42.0 | 1119.2 | – | – | 16384 | – | sourced | – | source |
| M4 Max | Qwen3 8B | 8bit | oMLX | 41.1 | 719.1 | – | – | 4096 | 2026-10-12 | community | – | source |
| RTX 5070 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 40.4 | 1078.7 | – | – | 65536 | – | sourced | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 39.9 | 1152.6 | – | – | 65536 | – | sourced | – | source |
| RTX 4080 SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 39.1 | 1501.5 | – | – | 65536 | – | sourced | – | source |
| RTX 4080 | Qwen3 8B 8B | Q4_K | llama.cpp | 39.0 | 937.9 | – | – | 65536 | – | sourced | – | source |
| RTX 5060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 38.9 | 915.1 | – | – | 32768 | – | sourced | – | source |
| RTX 4070 | Qwen3 8B 8B | Q4_K | llama.cpp | 38.1 | 1116.7 | – | – | 32768 | – | sourced | – | source |
| RTX Pro 5000 Blackwell | Qwen3 8B 8B | Q4_K | llama.cpp | 38.1 | 899.1 | – | – | 131072 | – | sourced | – | source |
| M4 Max | Qwen3 8B | 8bit | oMLX | 36.7 | 663.2 | – | – | 8192 | 2026-10-12 | community | – | source |
| RTX 4070 Ti SUPER | Qwen3 8B 8B | Q4_K | llama.cpp | 36.6 | 829.4 | – | – | 65536 | – | sourced | – | source |
| RTX 4060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 34.3 | 1480.8 | – | – | 16384 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B 8B | Q4_K | llama.cpp | 33.8 | 1059.9 | – | – | 131072 | – | sourced | – | source |
| RTX 4090 | Qwen3 8B | Q4_K_M | llama.cpp llama-bench | 33.8 | – | – | – | 131072 | 2026-08-17 | sourced | – | source |
| RTX 3060 12GB | Qwen3 8B 8B | Q4_K | llama.cpp | 31.9 | 764.7 | – | – | 32768 | – | sourced | – | source |
| M1 Pro | Qwen3 8B | 4bit | oMLX | 31.7 | 167.6 | – | – | 4096 | 2026-10-15 | community | – | source |
| M4 Pro | Qwen3 8B | 4bit | oMLX | 31.1 | 362.6 | – | – | 16384 | 2026-10-11 | community | – | source |
| M6 | Qwen3 8B | 4bit | oMLX | 29.6 | 1085.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| RTX 3090 Ti | Qwen3 8B 8B | Q4_K | llama.cpp | 29.0 | 612.4 | – | – | 131072 | – | sourced | – | source |
| M4 Pro | Qwen3 8B | 4bit | oMLX | 28.5 | 291.2 | – | – | 16384 | 2026-10-13 | community | – | source |
| M1 Max | Qwen3 8B | 4bit | oMLX | 28.2 | 242.2 | – | – | 32768 | 2026-10-08 | community | – | source |
| M5 | Qwen3 8B | 4bit | oMLX | 28.0 | 755.6 | – | – | 1024 | 2026-10-07 | community | – | source |
| RTX A6000 | Qwen3 8B 8B | Q4_K | llama.cpp | 27.9 | 951.0 | – | – | 65536 | – | sourced | – | source |
| M5 | Qwen3 8B | 4bit | oMLX | 27.1 | 845.3 | – | – | 1024 | 2026-10-11 | community | – | source |
| M5 | Qwen3 8B | 4bit | oMLX | 27.1 | 845.3 | – | – | 1024 | 2026-10-11 | community | – | source |
| M6 | Qwen3 8B | 4bit | oMLX | 26.2 | 1041.0 | – | – | 4096 | 2026-10-10 | community | – | source |
| RTX 5060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 25.8 | 529.8 | – | – | 65536 | – | sourced | – | source |
| M5 | Qwen3 8B | 4bit | oMLX | 25.7 | 747.7 | – | – | 4096 | 2026-10-07 | community | – | source |
| RTX 4060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 25.5 | 760.3 | – | – | 32768 | – | sourced | – | source |
| M5 | Qwen3 8B | 4bit | oMLX | 24.7 | 847.5 | – | – | 4096 | 2026-10-11 | community | – | source |
| M5 | Qwen3 8B | 4bit | oMLX | 24.7 | 847.5 | – | – | 4096 | 2026-10-11 | community | – | source |
| M1 Pro | Qwen3 8B | 4bit | oMLX | 22.3 | 135.7 | – | – | 16384 | 2026-10-15 | community | – | source |
| RTX 6000 Ada | Qwen3 8B 8B | Q4_K | llama.cpp | 20.8 | 541.3 | – | – | 131072 | – | sourced | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 20.3 | 225.1 | – | – | 4096 | 2026-10-08 | community | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 19.9 | 233.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 19.4 | 195.4 | – | – | 4096 | 2026-10-16 | community | – | source |
| M1 Max | Qwen3 8B | 4bit | oMLX | 19.0 | 171.1 | – | – | 65536 | 2026-10-08 | community | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 18.8 | 220.5 | – | – | 4096 | 2026-10-07 | community | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 18.3 | 210.7 | – | – | 8192 | 2026-10-14 | community | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 17.7 | 219.2 | – | – | 4096 | 2026-10-10 | community | contradiction | source |
| M2 | Qwen3 8B | 4bit | oMLX | 16.7 | 128.9 | – | – | 4096 | 2026-10-12 | community | – | source |
| RTX A6000 | Qwen3 8B 8B | Q4_K | llama.cpp | 16.0 | 527.9 | – | – | 131072 | – | sourced | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 13.3 | 174.0 | – | – | 16384 | 2026-10-08 | community | – | source |
| RTX 4060 Ti 16GB | Qwen3 8B 8B | Q4_K | llama.cpp | 13.0 | 392.1 | – | – | 65536 | – | sourced | – | source |
| M4 | Qwen3 8B | 4bit | oMLX | 12.9 | 153.2 | – | – | 16384 | 2026-10-16 | community | – | source |
| M2 | Qwen3 8B | 4bit | oMLX | 11.9 | 105.0 | – | – | 16384 | 2026-10-12 | community | – | source |
| H100 NVL | Qwen3 8B | FP8 | vLLM | – | 1202 | – | – | – | 2026-10-07 | community | – | source |
| H100 NVL | Qwen3 8B | FP8 | vLLM | – | 4160 | – | – | – | 2026-10-07 | community | – | source |
| H100 NVL | Qwen3 8B | FP8 | vLLM | – | 529 | – | – | – | 2026-10-07 | community | – | source |
| H100 NVL | Qwen3 8B | FP8 | vLLM | – | 634 | – | – | – | 2026-10-07 | community | – | source |