Benchmark reports

999 reports · Newest first · Page 35 / 40

1. Qwen3-8B-FP8

   /root/autodl-tmp/modelscope/Qwen/Qwen3-8B-FP8

   2 × RTX 5090 · 32 GB

   Text generation · FP8 · vLLM-DP2

   2026-01-15 08:23:30View report ↗

2. Qwen3-4B-Instruct-FP8

   /root/autodl-tmp/modelscope/Qwen/Qwen3-4B-Instruct-2507-FP8

   2 × RTX 5090 · 32 GB

   Text generation · FP8 · vLLM-DP2

   2026-01-15 08:13:31View report ↗

3. Qwen3-4B-Thinking-FP8

   /root/autodl-tmp/modelscope/Qwen/Qwen3-4B-Thinking-2507-FP8

   2 × RTX 5090 · 32 GB

   Text generation · FP8 · vLLM-DP2

   2026-01-15 08:04:23View report ↗

4. Qwen3-4B-FP8

   /root/autodl-tmp/modelscope/Qwen/Qwen3-4B-FP8

   2 × RTX 5090 · 32 GB

   Text generation · FP8 · vLLM-DP2

   2026-01-15 07:22:48View report ↗

5. Qwen3-1.7B-FP8

   /root/autodl-tmp/modelscope/Qwen/Qwen3-1___7B-FP8

   2 × RTX 5090 · 32 GB

   Text generation · FP8 · vLLM-DP2

   2026-01-15 07:06:29View report ↗

6. Qwen3-0.6B-FP8

   /root/autodl-tmp/modelscope/Qwen/Qwen3-0___6B-FP8

   2 × RTX 5090 · 32 GB

   Text generation · FP8 · vLLM-DP2

   2026-01-15 06:51:06View report ↗

7. Qwen3-32B-AWQ

   /root/.cache/huggingface/hub/models--Qwen--Qwen3-32B-AWQ/snapshots/0499c3ac83fdef8810b907a23894ba91e95eddd8

   A100-SXM4-80GB · 80 GB

   Text generation · AWQ · vLLM

   2026-01-15 04:40:01View report ↗

8. Qwen3-0.6B-FP8

   /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-0.6B-FP8/snapshots/e5be08033360965ceca7b0ffd72d521a51331ce0

   B200 · 179 GB

   Text generation · FP8 · vLLM

   2026-01-15 01:06:38View report ↗

9. Qwen3-1.7B-FP8

   /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B-FP8/snapshots/1641e6c1b620b7ed7e8711b443990429a23b1b99

   B200 · 179 GB

   Text generation · FP8 · vLLM

   2026-01-15 00:56:08View report ↗

10. Qwen3-4B-Thinking-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Thinking-2507-FP8/snapshots/953532f942706930ec4bb870569932ef63038fdf

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-15 00:44:52View report ↗

11. Qwen3-4B-Instruct-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507-FP8/snapshots/8591804019c8b22094c3b5b4454e0edc05dffc98

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-15 00:33:25View report ↗

12. Qwen3-30B-A3B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-30B-A3B-Instruct-2507-FP8/snapshots/5a5a776300a41aaa681dd7ff0106608ef2bc90db

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-15 00:24:54View report ↗

13. Qwen3-30B-A3B-Thinking-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-30B-A3B-Thinking-2507-FP8/snapshots/60d80c83c53c3b611c642dbb8c942b3f90c5948a

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-15 00:16:00View report ↗

14. Qwen3-30B-A3B-Thinking-FP8

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-30B-A3B-Thinking-2507-FP8

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-14 21:16:49View report ↗

15. Qwen3-30B-A3B-FP8

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-14 21:04:30View report ↗

16. Qwen3-32B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-32B-FP8/snapshots/aa55da1ecc13d006e8b8e4f54579b1ea8c3db2df

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 21:01:19View report ↗

17. Qwen3-4B-Instruct-FP8

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507-FP8

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-14 20:52:10View report ↗

18. Qwen3-14B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-14B-FP8/snapshots/9a283b4a5efbc09ce247e0ae5b02b744739e525a

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 20:51:34View report ↗

19. Qwen3-8B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-8B-FP8/snapshots/220b46e3b2180893580a4454f21f22d3ebb187d3

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 20:42:55View report ↗

20. Qwen3-4B-Thinking-FP8

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Thinking-2507-FP8

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-14 20:40:29View report ↗

21. Qwen3-4B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-4B-FP8/snapshots/96b30dc13593a244a5e59e84687309f53c375cfa

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 20:31:06View report ↗

22. Qwen3-VL-2B

    /root/.cache/huggingface/hub/models--Qwen--Qwen3-VL-2B-Instruct/snapshots/89644892e4d85e24eaac8bacfd4f463576704203

    A100-SXM4-80GB · 80 GB

    Text generation · BF16 · vLLM

    2026-01-14 20:17:21View report ↗

23. Hunyuan-1.8B-FP8

    /home/tiger/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-1___8B-FP8

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 20:02:56View report ↗

24. Qwen3-1.7B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B-FP8/snapshots/1641e6c1b620b7ed7e8711b443990429a23b1b99

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 19:50:46View report ↗

25. Qwen3-0.6B-FP8

    /home/tiger/.cache/huggingface/hub/models--Qwen--Qwen3-0.6B-FP8/snapshots/e5be08033360965ceca7b0ffd72d521a51331ce0

    B200 · 179 GB

    Text generation · FP8 · vLLM

    2026-01-14 19:41:48View report ↗

Updated 2026-11-12T01:13:00.539Z