Benchmark reports

999 reports · Newest first · Page 34 / 40

1. qwen3:0.6b

   qwen3:0.6b

   Apple M2 Max GPU (38-core) · 48 GB

   Text generation · Ollama · vLLM

   2026-01-15 18:49:13View report ↗

2. Qwen3-VL-2B-FP8

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-15 16:26:39View report ↗

3. Qwen3-0.6B

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

   RTX 4090D · 48 GB

   Text generation · BF16 · vLLM

   2026-01-15 15:37:15View report ↗

4. Qwen3-1.7B

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

   RTX 4090D · 48 GB

   Text generation · BF16 · vLLM

   2026-01-15 15:23:17View report ↗

5. Qwen3-4B

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

   RTX 4090D · 48 GB

   Text generation · BF16 · vLLM

   2026-01-15 15:11:58View report ↗

6. Qwen3-32B-AWQ

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

   RTX 4090D · 48 GB

   Text generation · AWQ · vLLM

   2026-01-15 14:56:53View report ↗

7. Qwen3-14B-AWQ

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

   RTX 4090D · 48 GB

   Text generation · AWQ · vLLM

   2026-01-15 14:44:05View report ↗

8. Qwen3-8B-AWQ

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

   RTX 4090D · 48 GB

   Text generation · AWQ · vLLM

   2026-01-15 14:32:20View report ↗

9. Qwen3-4B-AWQ

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

   RTX 4090D · 48 GB

   Text generation · AWQ · vLLM

   2026-01-15 14:21:39View report ↗

10. Qwen3-32B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 11:46:15View report ↗

11. Qwen3-30B-A3B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 11:33:06View report ↗

12. Qwen3-14B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 11:19:25View report ↗

13. 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

    2026-01-15 10:55:10View report ↗

14. Qwen3-1.7B-FP8

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

    RTX 4090 · 24 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:51:57View report ↗

15. Qwen3-8B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:50:17View report ↗

16. Qwen3-4B-Instruct-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:38:39View report ↗

17. Qwen3-0.6B-FP8

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

    RTX 4090 · 24 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:34:01View report ↗

18. Qwen3-4B-Thinking-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:26:57View report ↗

19. Qwen3-4B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:15:35View report ↗

20. Qwen3-4B-AWQ

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

    7 × RTX 3080 · 10 GB

    Text generation · AWQ · vLLM

    2026-01-15 10:10:06View report ↗

21. Qwen3-1.7B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 10:01:35View report ↗

22. Qwen3-1.7B

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

    7 × RTX 3080 · 10 GB

    Text generation · BF16 · vLLM

    2026-01-15 09:52:50View report ↗

23. Qwen3-0.6B-FP8

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

    RTX 4090D · 48 GB

    Text generation · FP8 · vLLM

    2026-01-15 09:46:46View report ↗

24. Qwen3-0.6B

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

    7 × RTX 3080 · 10 GB

    Text generation · BF16 · vLLM-DP7

    2026-01-15 09:08:58View report ↗

25. Qwen3-14B-FP8

    /root/autodl-tmp/modelscope/Qwen/Qwen3-14B-FP8

    2 × RTX 5090 · 32 GB

    Text generation · FP8 · vLLM-DP2

    2026-01-15 08:25:46View report ↗

Updated 2026-11-12T00:28:29.758Z