Benchmark reports

999 reports · Newest first · Page 32 / 40

1. Qwen3-4B-Q8_0

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q8_0.gguf

   RTX 4090D · 48 GB

   Text generation · Q8_0 · vLLM

   2026-01-20 19:36:44View report ↗

2. Qwen3-4B-Q5_K_M

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q5_K_M.gguf

   RTX 4090D · 48 GB

   Text generation · Q5_K_M · vLLM

   2026-01-20 19:34:50View report ↗

3. Qwen3-4B-Q4_K_M

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q4_K_M.gguf

   RTX 4090D · 48 GB

   Text generation · Q4_K_M · vLLM

   2026-01-20 19:32:56View report ↗

4. HY-MT1.5-1.8B-Q8_0

   /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-1___8B-GGUF/HY-MT1.5-1.8B-Q8_0.gguf

   RTX 4090D · 48 GB

   Text generation · Q8_0 · vLLM

   2026-01-20 19:31:06View report ↗

5. HY-MT1.5-1.8B-Q6_K

   /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-1___8B-GGUF/HY-MT1.5-1.8B-Q6_K.gguf

   RTX 4090D · 48 GB

   Text generation · Q6_K · vLLM

   2026-01-20 19:29:13View report ↗

6. HY-MT1.5-1.8B-Q4_K_M

   /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-1___8B-GGUF/HY-MT1.5-1.8B-Q4_K_M.gguf

   RTX 4090D · 48 GB

   Text generation · Q4_K_M · vLLM

   2026-01-20 19:27:24View report ↗

7. Qwen3-1.7B-Q8_0

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-1___7B-GGUF/Qwen3-1.7B-Q8_0.gguf

   RTX 4090D · 48 GB

   Text generation · Q8_0 · vLLM

   2026-01-20 19:25:35View report ↗

8. Qwen3-0.6B-Q8_0

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-0___6B-GGUF/Qwen3-0.6B-Q8_0.gguf

   RTX 4090D · 48 GB

   Text generation · Q8_0 · vLLM

   2026-01-20 19:23:44View report ↗

9. Qwen3-32B-Q4_K_M

   /root/.cache/modelscope/hub/models/Qwen/Qwen3-32B-GGUF/Qwen3-32B-Q4_K_M.gguf

   RTX 4090D · 48 GB

   Text generation · Q4_K_M · vLLM

   2026-01-20 17:05:10View report ↗

10. Qwen3-30B-A3B-Q8_0

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-30B-A3B-GGUF/Qwen3-30B-A3B-Q8_0.gguf

    RTX 4090D · 48 GB

    Text generation · Q8_0 · vLLM

    2026-01-20 16:56:37View report ↗

11. Qwen3-30B-A3B-Q4_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-30B-A3B-GGUF/Qwen3-30B-A3B-Q4_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-20 16:22:46View report ↗

12. Qwen3-14B-Q8_0

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-GGUF/Qwen3-14B-Q8_0.gguf

    RTX 4090D · 48 GB

    Text generation · Q8_0 · vLLM

    2026-01-20 16:13:41View report ↗

13. Qwen3-14B-Q5_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-GGUF/Qwen3-14B-Q5_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q5_K_M · vLLM

    2026-01-20 16:07:27View report ↗

14. Qwen3-14B-Q4_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-14B-GGUF/Qwen3-14B-Q4_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-20 16:02:01View report ↗

15. Qwen3-8B-Q8_0

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-GGUF/Qwen3-8B-Q8_0.gguf

    RTX 4090D · 48 GB

    Text generation · Q8_0 · vLLM

    2026-01-20 15:57:45View report ↗

16. Qwen3-8B-Q5_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-GGUF/Qwen3-8B-Q5_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q5_K_M · vLLM

    2026-01-20 15:54:34View report ↗

17. Qwen3-8B-Q4_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-8B-GGUF/Qwen3-8B-Q4_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-20 15:52:22View report ↗

18. HY-MT1.5-7B-Q8_0

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-7B-GGUF/HY-MT1.5-7B-Q8_0.gguf

    RTX 4090D · 48 GB

    Text generation · Q8_0 · vLLM

    2026-01-20 15:50:25View report ↗

19. HY-MT1.5-7B-Q6_K

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-7B-GGUF/HY-MT1.5-7B-Q6_K.gguf

    RTX 4090D · 48 GB

    Text generation · Q6_K · vLLM

    2026-01-20 15:46:40View report ↗

20. HY-MT1.5-7B-Q4_K_M

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-7B-GGUF/HY-MT1.5-7B-Q4_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-20 15:44:03View report ↗

21. Qwen3-4B-Q8_0

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q8_0.gguf

    RTX 4090D · 48 GB

    Text generation · Q8_0 · vLLM

    2026-01-20 15:42:08View report ↗

22. Qwen3-4B-Q5_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q5_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q5_K_M · vLLM

    2026-01-20 15:40:15View report ↗

23. Qwen3-4B-Q4_K_M

    /root/.cache/modelscope/hub/models/Qwen/Qwen3-4B-GGUF/Qwen3-4B-Q4_K_M.gguf

    RTX 4090D · 48 GB

    Text generation · Q4_K_M · vLLM

    2026-01-20 15:38:19View report ↗

24. HY-MT1.5-1.8B-Q8_0

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-1___8B-GGUF/HY-MT1.5-1.8B-Q8_0.gguf

    RTX 4090D · 48 GB

    Text generation · Q8_0 · vLLM

    2026-01-20 15:36:24View report ↗

25. HY-MT1.5-1.8B-Q6_K

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/HY-MT1___5-1___8B-GGUF/HY-MT1.5-1.8B-Q6_K.gguf

    RTX 4090D · 48 GB

    Text generation · Q6_K · vLLM

    2026-01-20 15:34:32View report ↗

Updated 2026-11-11T23:01:58.266Z