Benchmark reports

999 reports · Newest first · Page 11 / 40

1. Qwen3-4B-FP8

   Qwen/Qwen3-4B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:41:14View report ↗

2. Qwen3-1.7B-FP8

   Qwen/Qwen3-1.7B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:22:05View report ↗

3. Qwen3-1.7B-FP8

   Qwen/Qwen3-1.7B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:20:45View report ↗

4. Qwen3-1.7B-FP8

   Qwen/Qwen3-1.7B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:19:47View report ↗

5. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:17:31View report ↗

6. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:16:39View report ↗

7. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 14:16:05View report ↗

8. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 13:22:12View report ↗

9. Qwen3-0.6B-FP8

   Qwen/Qwen3-0.6B-FP8

   L4 · 24 GB

   Text generation · FP8 · vllm

   2026-10-18 12:25:46View report ↗

10. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-17 02:30:19View report ↗

11. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-17 01:50:19View report ↗

12. MiniCPM-V-4.7-35B-A3B-NVFP4

    sambit9238/MiniCPM-V-4.7-35B-A3B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-16 07:41:21View report ↗

13. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-16 02:11:58View report ↗

14. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-15 22:05:56View report ↗

15. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-15 21:47:06View report ↗

16. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-15 21:23:17View report ↗

17. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-15 20:57:08View report ↗

18. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-15 15:55:03View report ↗

19. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-15 09:27:35View report ↗

20. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-15 09:07:41View report ↗

21. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 4090D · 48 GB

    Text generation · NVFP4 · vllm

    2026-10-15 06:20:58View report ↗

22. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-15 06:11:39View report ↗

23. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-15 05:03:15View report ↗

24. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-14 23:18:43View report ↗

25. Qwen3.8-27B-NVFP4

    RadixArk/Qwen3.8-27B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vllm

    2026-10-14 23:18:21View report ↗

Updated 2026-11-06T15:07:33.925Z