Benchmark reports

999 reports · Newest first · Page 36 / 40

1. Qwen3-0.6B

   /dev/shm/gpullmbench_models/modelscope/Qwen/Qwen3-0___6B

   A100-SXM4-80GB · 80 GB

   Text generation · BF16 · vLLM

   2026-01-14 19:12:53View report ↗

2. Qwen3-0.6B

   /root/.cache/huggingface/hub/models--Qwen--Qwen3-0.6B/snapshots/c1899de289a04d12100db370d81485cdf75e47ca

   A100-SXM4-80GB · 80 GB

   Text generation · BF16 · vLLM

   2026-01-14 19:11:30View report ↗

3. Qwen3-1.7B

   /root/.cache/huggingface/hub/models--Qwen--Qwen3-1.7B/snapshots/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e

   A100-SXM4-80GB · 80 GB

   Text generation · BF16 · vLLM

   2026-01-14 17:02:01View report ↗

4. Qwen3-0.6B

   /root/.cache/huggingface/hub/models--Qwen--Qwen3-0.6B/snapshots/c1899de289a04d12100db370d81485cdf75e47ca

   A100-SXM4-80GB · 80 GB

   Text generation · BF16 · vLLM

   2026-01-14 16:01:11View report ↗

5. Qwen2.5-72B-AWQ

   /root/.cache/modelscope/hub/models/Qwen/Qwen2___5-72B-Instruct-AWQ

   RTX 4090D · 48 GB

   Text generation · AWQ · vLLM

   2026-01-14 08:15:40View report ↗

6. Qwen3-VL-32B-FP8

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-32B-Instruct-FP8

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-14 04:56:43View report ↗

7. Qwen3-VL-32B-FP8

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-32B-Instruct-FP8

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-14 04:34:55View report ↗

8. Qwen3-32B-FP8

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-14 04:14:36View report ↗

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

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-14 03:16:16View report ↗

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

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 11:57:27View report ↗

11. Qwen3-14B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 11:51:54View report ↗

12. Qwen3-VL-8B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 11:38:12View report ↗

13. Qwen3-8B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 11:26:08View report ↗

14. 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 11:14:03View report ↗

15. 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 11:02:52View report ↗

16. Qwen3-4B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 10:52:27View report ↗

17. Qwen3-VL-2B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 10:40:59View report ↗

18. Qwen3-0.6B-FP8

    /home/lyx/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 10:38:28View report ↗

19. Hunyuan-1.8B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 10:28:46View report ↗

20. Qwen3-1.7B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 10:17:22View report ↗

21. Qwen3-0.6B-FP8

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-FP8

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-13 10:05:45View report ↗

22. Qwen3-VL-32B-FP8

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

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 08:53:29View report ↗

23. Qwen3-VL-32B-Instruct

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

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · Native · vLLM

    2026-01-13 08:23:02View report ↗

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

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

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · FP8 · vLLM

    2026-01-13 07:56:40View report ↗

25. Qwen3-VL-30B-A3B-Instruct

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

    RTX PRO 6000 Blackwell Workstation Edition · 96 GB

    Text generation · Native · vLLM

    2026-01-13 07:39:24View report ↗

Updated 2026-11-12T02:07:02.748Z