Benchmark reports

999 reports · Newest first · Page 18 / 40

1. Qwen3.5-2B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-2B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 03:00:54View report ↗

2. Qwen3.5-4B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-4B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 02:25:01View report ↗

3. Qwen3.5-2B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-2B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 02:16:29View report ↗

4. Qwen3.5-0.8B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-0.8B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 02:06:36View report ↗

5. Qwen3.5-0.8B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-0.8B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 02:04:58View report ↗

6. Qwen3.5-0.8B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-0.8B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 01:58:36View report ↗

7. Qwen3.6-27B-AWQ

   /root/.cache/modelscope/models/tclf90--Qwen3.6-27B-AWQ/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · AWQ · vLLM

   2026-10-07 01:13:02View report ↗

8. Qwen3.5-4B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-4B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 01:09:00View report ↗

9. Qwen3.5-2B

   /root/.cache/modelscope/models/Qwen--Qwen3.5-2B/snapshots/master

   vGPU-32GB · 32 GB

   Text generation · BF16 · vLLM

   2026-10-07 01:08:42View report ↗

10. Qwen3.5-0.8B

    /root/.cache/modelscope/models/Qwen--Qwen3.5-0.8B/snapshots/master

    vGPU-32GB · 32 GB

    Text generation · BF16 · vLLM

    2026-10-07 01:08:27View report ↗

11. Qwen3-0.6B

    /root/.cache/modelscope/models/Qwen--Qwen3-0.6B/snapshots/master

    vGPU-32GB · 32 GB

    Text generation · Native · vLLM

    2026-10-06 23:42:32View report ↗

12. Qwen3-0.6B

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

    A100-SXM4-40GB · 40 GB

    Text generation · BF16 · vLLM

    2026-05-29 03:10:44View report ↗

13. Qwen3-4B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-05-23 18:29:46View report ↗

14. Hunyuan-MT2-1.8B-FP8

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/Hy-MT2-1___8B-FP8

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-05-23 18:17:06View report ↗

15. Qwen3-1.7B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-05-23 18:07:36View report ↗

16. Qwen3-0.6B-FP8

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

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-05-23 17:58:21View report ↗

17. Qwen3-14B-NVFP4

    /root/.cache/modelscope/hub/models/RedHatAI/Qwen3-14B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vLLM

    2026-05-23 17:50:20View report ↗

18. Qwen3-8B-NVFP4

    /root/.cache/modelscope/hub/models/RedHatAI/Qwen3-8B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vLLM

    2026-05-23 17:31:13View report ↗

19. ChatTTS

    2Noise/ChatTTS

    RTX 5090 · 32 GB

    Speech synthesis · fp16 · vLLM

    2026-05-23 11:23:08View report ↗

20. whisper-large-v3-turbo

    openai/whisper-large-v3-turbo

    RTX 5090 · 32 GB

    Speech recognition · fp16 · vLLM

    2026-05-23 11:12:26View report ↗

21. qwen3:0.6b

    qwen3:0.6b

    RTX 5090 · 32 GB

    Text generation · Ollama · vLLM

    2026-05-23 09:59:11View report ↗

22. Qwen3-0.6B-Q8

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

    RTX 5090 · 32 GB

    Text generation · Q8_0 · vLLM

    2026-05-23 08:34:45View report ↗

23. Hunyuan-MT2-7B-FP8

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/Hy-MT2-7B-FP8

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-05-23 08:08:15View report ↗

24. Qwen3-8B-NVFP4

    /root/.cache/modelscope/hub/models/RedHatAI/Qwen3-8B-NVFP4

    RTX 5090 · 32 GB

    Text generation · NVFP4 · vLLM

    2026-05-23 07:52:06View report ↗

25. Hunyuan-MT2-1.8B-FP8

    /root/.cache/modelscope/hub/models/Tencent-Hunyuan/Hy-MT2-1___8B-FP8

    RTX 5090 · 32 GB

    Text generation · FP8 · vLLM

    2026-05-23 07:16:29View report ↗

Updated 2026-11-11T12:35:11.355Z