Benchmark reports

999 reports · Newest first · Page 7 / 40

1. Qwen3.8-27B-NVFP4

   RadixArk/Qwen3.8-27B-NVFP4

   RTX PRO 6000 Blackwell Server Edition · 96 GB

   Text generation · NVFP4 · vllm

   2026-10-18 23:46:41View report ↗

2. Qwen3.8-27B-NVFP4

   RadixArk/Qwen3.8-27B-NVFP4

   RTX PRO 6000 Blackwell Server Edition · 96 GB

   Text generation · NVFP4 · vllm

   2026-10-18 23:22:38View report ↗

3. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 20:02:34View report ↗

4. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 20:01:15View report ↗

5. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 20:00:32View report ↗

6. NVIDIA-Nemotron-Nano-12B-v2-VL-NVFP4-QAD

   nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-NVFP4-QAD

   RTX PRO 6000 Blackwell Server Edition · 96 GB

   Text generation · NVFP4 · vllm

   2026-10-18 18:21:34View report ↗

7. NVIDIA-Nemotron-Nano-12B-v2-VL-NVFP4-QAD

   nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-NVFP4-QAD

   RTX PRO 6000 Blackwell Server Edition · 96 GB

   Text generation · NVFP4 · vllm

   2026-10-18 18:20:57View report ↗

8. Qwen3-4B-AWQ

   Qwen/Qwen3-4B-AWQ

   T4 · 16 GB

   Text generation · AWQ · vllm

   2026-10-18 18:19:09View report ↗

9. NVIDIA-Nemotron-Nano-9B-v2-NVFP4

   nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4

   RTX PRO 6000 Blackwell Server Edition · 96 GB

   Text generation · NVFP4 · vllm

   2026-10-18 18:16:58View report ↗

10. Qwen3-1.7B-FP8

    Qwen/Qwen3-1.7B-FP8

    L4 · 24 GB

    Text generation · FP8 · vllm

    2026-10-18 18:16:30View report ↗

11. NVIDIA-Nemotron-Nano-9B-v2-NVFP4

    nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:16:28View report ↗

12. NVIDIA-Nemotron-Nano-9B-v2-NVFP4

    nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:15:49View report ↗

13. Qwen3-1.7B-FP8

    Qwen/Qwen3-1.7B-FP8

    L4 · 24 GB

    Text generation · FP8 · vllm

    2026-10-18 18:15:00View report ↗

14. Qwen3-1.7B-FP8

    Qwen/Qwen3-1.7B-FP8

    L4 · 24 GB

    Text generation · FP8 · vllm

    2026-10-18 18:13:58View report ↗

15. Qwen3-0.6B-GPTQ-Int8

    Qwen/Qwen3-0.6B-GPTQ-Int8

    T4 · 16 GB

    Text generation · GPTQ · vllm

    2026-10-18 18:12:44View report ↗

16. Llama-3.1-8B-Instruct-NVFP4

    nvidia/Llama-3.1-8B-Instruct-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:12:13View report ↗

17. Llama-3.1-8B-Instruct-NVFP4

    nvidia/Llama-3.1-8B-Instruct-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:11:46View report ↗

18. Llama-3.1-8B-Instruct-NVFP4

    nvidia/Llama-3.1-8B-Instruct-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:11:21View report ↗

19. Qwen3-0.6B-FP8

    Qwen/Qwen3-0.6B-FP8

    L4 · 24 GB

    Text generation · FP8 · vllm

    2026-10-18 18:09:14View report ↗

20. Qwen3-8B-NVFP4

    RedHatAI/Qwen3-8B-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:08:42View report ↗

21. Qwen3-0.6B-GPTQ-Int8

    Qwen/Qwen3-0.6B-GPTQ-Int8

    T4 · 16 GB

    Text generation · GPTQ · vllm

    2026-10-18 18:08:22View report ↗

22. Qwen3-0.6B-FP8

    Qwen/Qwen3-0.6B-FP8

    L4 · 24 GB

    Text generation · FP8 · vllm

    2026-10-18 18:08:19View report ↗

23. Qwen3-8B-NVFP4

    RedHatAI/Qwen3-8B-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:08:10View report ↗

24. Qwen3-8B-NVFP4

    RedHatAI/Qwen3-8B-NVFP4

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · NVFP4 · vllm

    2026-10-18 18:07:42View report ↗

25. Qwen3-0.6B-FP8

    Qwen/Qwen3-0.6B-FP8

    L4 · 24 GB

    Text generation · FP8 · vllm

    2026-10-18 18:07:39View report ↗

Updated 2026-11-06T02:56:49.075Z