Benchmark reports

999 reports · Newest first · Page 17 / 40

1. Kokoro-82M

   hexgrad/Kokoro-82M

   vGPU-32GB · 32 GB

   Speech synthesis · fp32 · kokoro

   2026-10-08 03:30:29View report ↗

2. faster-whisper-tiny

   Systran/faster-whisper-tiny

   vGPU-32GB · 32 GB

   Speech recognition · fp16 · faster-whisper

   2026-10-08 03:28:14View report ↗

3. qwen3.8-flash-next-q2_0

   qwen3.8-flash-next-q2_0

   RTX 3080 Ti · 12 GB

   Text generation · Q2_0 · strata

   2026-10-08 00:57:21View report ↗

4. Kokoro-82M

   hexgrad/Kokoro-82M

   RTX 3080 Ti · 12 GB

   Speech synthesis · fp32 · kokoro

   2026-10-08 00:50:51View report ↗

5. SenseVoiceSmall

   iic/SenseVoiceSmall

   RTX 3080 Ti · 12 GB

   Speech recognition · fp16 · funasr

   2026-10-08 00:41:46View report ↗

6. faster-whisper-tiny

   Systran/faster-whisper-tiny

   RTX 3080 Ti · 12 GB

   Speech recognition · fp16 · faster-whisper

   2026-10-08 00:41:29View report ↗

7. clef-flash

   ms:Cloudflare/clef-flash

   vGPU-32GB · 32 GB

   Decision · bf16 · clef-native

   2026-10-07 12:59:49View report ↗

8. whisper-tiny

   openai/whisper-tiny

   vGPU-32GB · 32 GB

   Speech recognition · fp16 · faster-whisper

   2026-10-07 12:54:21View report ↗

9. Kokoro-82M

   hexgrad/Kokoro-82M

   vGPU-32GB · 32 GB

   Speech synthesis · fp32 · kokoro

   2026-10-07 12:54:04View report ↗

10. clef-flash

    ms:Cloudflare/clef-flash

    vGPU-32GB · 32 GB

    Decision · bf16 · clef-native

    2026-10-07 12:51:07View report ↗

11. embeddinggemma-2

    ms:google/embeddinggemma-2

    vGPU-32GB · 32 GB

    Embedding · bf16 · sentence-transformers

    2026-10-07 12:50:28View report ↗

12. embeddinggemma-2

    ms:google/embeddinggemma-2

    vGPU-32GB · 32 GB

    Embedding · bf16 · sentence-transformers

    2026-10-07 11:13:47View report ↗

13. clef-flash

    ms:Cloudflare/clef-flash

    vGPU-32GB · 32 GB

    Decision · bf16 · clef-native

    2026-10-07 11:11:06View report ↗

14. embeddinggemma-2

    ms:google/embeddinggemma-2

    vGPU-32GB · 32 GB

    Embedding · bf16 · sentence-transformers

    2026-10-07 11:10:25View report ↗

15. embeddinggemma-2

    ms:google/embeddinggemma-2

    vGPU-32GB · 32 GB

    Embedding · bf16 · sentence-transformers

    2026-10-07 10:43:37View report ↗

16. whisper-tiny

    openai/whisper-tiny

    vGPU-32GB · 32 GB

    Speech recognition · fp16 · faster-whisper

    2026-10-07 10:25:46View report ↗

17. Kokoro-82M

    hexgrad/Kokoro-82M

    vGPU-32GB · 32 GB

    Speech synthesis · fp32 · kokoro

    2026-10-07 10:23:16View report ↗

18. clef-flash

    ms:Cloudflare/clef-flash

    vGPU-32GB · 32 GB

    Decision · bf16 · clef-native

    2026-10-07 10:22:12View report ↗

19. embeddinggemma-2

    ms:google/embeddinggemma-2

    vGPU-32GB · 32 GB

    Embedding · bf16 · sentence-transformers

    2026-10-07 10:21:19View report ↗

20. whisper-tiny

    openai/whisper-tiny

    vGPU-32GB · 32 GB

    Speech recognition · fp16 · faster-whisper

    2026-10-07 10:00:30View report ↗

21. clef-flash

    ms:Cloudflare/clef-flash

    vGPU-32GB · 32 GB

    Decision · bf16 · clef-native

    2026-10-07 09:55:46View report ↗

22. clef-flash

    ms:Cloudflare/clef-flash

    vGPU-32GB · 32 GB

    Decision · bf16 · vLLM

    2026-10-07 09:44:25View report ↗

23. Kokoro-82M

    hexgrad/Kokoro-82M

    vGPU-32GB · 32 GB

    Speech synthesis · fp32 · vLLM

    2026-10-07 09:40:16View report ↗

24. embeddinggemma-2

    ms:google/embeddinggemma-2

    vGPU-32GB · 32 GB

    Embedding · bf16 · sentence-transformers

    2026-10-07 09:34:33View report ↗

25. Qwen3-0.6B-Q8

    /root/.cache/modelscope/models/Qwen--Qwen3-0.6B-GGUF/snapshots/master/Qwen3-0.6B-Q8_0.gguf

    vGPU-32GB · 32 GB

    Text generation · Q8_0 · llama.cpp

    2026-10-07 08:12:16View report ↗

Updated 2026-11-11T11:38:39.550Z