Benchmark reports

999 reports · Newest first · Page 37 / 40

1. Qwen3-VL-8B-FP8

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct-FP8

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · FP8 · vLLM

   2026-01-13 07:13:46View report ↗

2. Qwen3-VL-8B-Instruct

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · Native · vLLM

   2026-01-13 06:54:15View report ↗

3. Qwen3-VL-4B-FP8

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct-FP8

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · FP8 · vLLM

   2026-01-13 06:40:36View report ↗

4. Qwen3-VL-4B-Instruct

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-VL-4B-Instruct

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · Native · vLLM

   2026-01-13 06:30:05View report ↗

5. Qwen3-VL-2B-FP8

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-VL-2B-Instruct-FP8

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · FP8 · vLLM

   2026-01-13 06:19:32View report ↗

6. Qwen3-VL-2B-Instruct

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-VL-2B-Instruct

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · Native · vLLM

   2026-01-13 06:10:43View report ↗

7. Qwen3-32B

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-32B

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · Native · vLLM

   2026-01-13 05:59:55View report ↗

8. Qwen3-30B-A3B

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-30B-A3B

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · Native · vLLM

   2026-01-13 05:27:56View report ↗

9. Qwen3-14B

   /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-14B

   RTX PRO 6000 Blackwell Workstation Edition · 96 GB

   Text generation · Native · vLLM

   2026-01-13 05:02:12View report ↗

10. Qwen3-8B

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-8B

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · Native · vLLM

    2026-01-13 04:43:56View report ↗

11. Qwen3-4B

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-4B

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · Native · vLLM

    2026-01-13 04:29:35View report ↗

12. Qwen3-1.7B

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · Native · vLLM

    2026-01-13 04:17:55View report ↗

13. Qwen3-0.6B

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · Native · vLLM

    2026-01-13 04:07:56View report ↗

14. Qwen3-30B-A3B-FP8

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

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 03:59:55View report ↗

15. Qwen3-32B-FP8

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-32B-FP8

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 03:39:20View report ↗

16. Qwen3-14B-FP8

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-14B-FP8

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 03:16:47View report ↗

17. Qwen3-8B-FP8

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-8B-FP8

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 03:02:20View report ↗

18. Qwen3-4B-FP8

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-4B-FP8

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 02:47:05View report ↗

19. Qwen3-VL-30B-A3B-FP8

    /root/autodl-tmp/modelscope/Qwen/Qwen3-VL-30B-A3B-Instruct-FP8

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:45:48View report ↗

20. Qwen3-32B-FP8

    /root/autodl-tmp/modelscope/Qwen/Qwen3-32B-FP8

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:35:30View report ↗

21. Hunyuan-7B-FP8

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-7B-FP8

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:34:54View report ↗

22. Qwen3-1.7B-FP8

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-FP8

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:30:18View report ↗

23. Qwen3-VL-4B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:30:03View report ↗

24. Qwen3-4B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:21:54View report ↗

25. Qwen3-VL-32B-FP8

    /root/autodl-tmp/modelscope/Qwen/Qwen3-VL-32B-Instruct-FP8

    RTX PRO 6000 Blackwell Server Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 01:19:39View report ↗

Updated 2026-11-12T02:42:34.448Z