Benchmark reports

999 reports · Newest first · Page 39 / 40

1. Qwen3-VL-2B-FP8

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-12 16:00:25View report ↗

2. 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

   2026-01-12 15:53:51View report ↗

3. Qwen3-1.7B-FP8

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-12 15:47:52View report ↗

4. Qwen3-0.6B-FP8

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-12 15:41:11View report ↗

5. Qwen3-30B-A3B-FP8

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

   RTX 4090D · 48 GB

   Text generation · FP8 · vLLM

   2026-01-12 13:35:23View report ↗

6. Qwen3-14B-FP8

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

   RTX 5090 · 32 GB

   Text generation · FP8 · vLLM

   2026-01-12 12:24:37View report ↗

7. Qwen3-14B-AWQ

   /home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen3-14B-AWQ

   RTX 3090 · 24 GB

   Text generation · AWQ · vLLM

   2026-01-12 12:22:46View report ↗

8. Qwen3-8B-FP8

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

   RTX 5090 · 32 GB

   Text generation · FP8 · vLLM

   2026-01-12 12:17:18View report ↗

9. Qwen3-8B-AWQ

   /home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen3-8B-AWQ

   RTX 3090 · 24 GB

   Text generation · AWQ · vLLM

   2026-01-12 12:15:24View report ↗

10. Qwen3-4B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-01-12 12:11:17View report ↗

11. Qwen3-4B

    /home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen3-4B

    RTX 3090 · 24 GB

    Text generation · BF16 · vLLM

    2026-01-12 12:08:00View report ↗

12. Qwen3-1.7B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-01-12 12:05:21View report ↗

13. Qwen3-1.7B

    /home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B

    RTX 3090 · 24 GB

    Text generation · BF16 · vLLM

    2026-01-12 12:00:47View report ↗

14. Qwen3-0.6B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-01-12 12:00:12View report ↗

15. Qwen3-0.6B

    /home/u20250324/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B

    RTX 3090 · 24 GB

    Text generation · BF16 · vLLM

    2026-01-12 11:54:49View report ↗

16. Qwen2.5-32B-Q4_K_M

    /Users/kanshan/.cache/modelscope/hub/models/qwen/Qwen2___5-32B-Instruct-GGUF/qwen2.5-32b-instruct-q4_k_m.gguf

    Apple M2 Max GPU (38-core) · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-12 10:56:16View report ↗

17. Qwen2.5-14B-Q4_K_M

    /Users/kanshan/.cache/modelscope/hub/models/qwen/Qwen2___5-14B-Instruct-GGUF/qwen2.5-14b-instruct-q4_k_m.gguf

    Apple M2 Max GPU (38-core) · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-12 10:39:19View report ↗

18. Qwen3-VL-8B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-01-12 10:34:38View report ↗

19. Qwen2.5-7B-Q4_K_M

    /Users/kanshan/.cache/modelscope/hub/models/qwen/Qwen2___5-7B-Instruct-GGUF/qwen2.5-7b-instruct-q4_k_m.gguf

    Apple M2 Max GPU (38-core) · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-12 10:33:35View report ↗

20. Qwen2.5-3B-Q4_K_M

    /Users/kanshan/.cache/modelscope/hub/models/qwen/Qwen2___5-3B-Instruct-GGUF/qwen2.5-3b-instruct-q4_k_m.gguf

    Apple M2 Max GPU (38-core) · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-12 10:30:02View report ↗

21. Qwen2.5-1.5B-Q4_K_M

    /Users/kanshan/.cache/modelscope/hub/models/qwen/Qwen2___5-1___5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q4_k_m.gguf

    Apple M2 Max GPU (38-core) · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-12 10:27:57View report ↗

22. Qwen2.5-0.5B-Q4_K_M

    /Users/kanshan/.cache/modelscope/hub/models/qwen/Qwen2___5-0___5B-Instruct-GGUF/qwen2.5-0.5b-instruct-q4_k_m.gguf

    Apple M2 Max GPU (38-core) · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-12 10:26:04View report ↗

23. Qwen3-VL-4B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-01-12 10:21:26View report ↗

24. Qwen3-VL-2B-FP8

    /root/autodl-tmp/modelscope/Qwen/Qwen3-VL-2B-Instruct-FP8

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-01-12 10:09:11View report ↗

25. Qwen3-VL-2B

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

    RTX 3080 · 10 GB

    Text generation · BF16 · vLLM

    2026-01-11 21:29:53View report ↗

Updated 2026-11-12T04:05:37.609Z