$ models — newest on hf · 30 tracked

1. 01
   Qwen3.6-35B-A3B-NVFP4@nvidia⬇ 11,298,952 · flat

   chat & code genapache-2.0 · commercial ✓base: Qwen/Qwen3.6-35B-A3B
2. 02
   Qwen3.6-35B-A3B-FP8@Qwen⬇ 8,946,336 · flat

   image-text-to-textapache-2.0 · commercial ✓base: Qwen/Qwen3.6-35B-A3B
3. 03
   gemma-4-26B-A4B-it@google⬇ 11,748,521 · flat

   image-text-to-textapache-2.0 · commercial ✓ctx 262,144$0.07/$0.34 per 1M tokbase: google/gemma-4-26B-A4B
4. 04
   gemma-4-31B-it@google⬇ 11,885,389 · flat

   image-text-to-textapache-2.0 · commercial ✓ctx 262,144$0.1/$0.34 per 1M tokbase: google/gemma-4-31B
5. 05
   Qwen3.5-9B@Qwen⬇ 12,403,996 · flat

   image-text-to-textapache-2.0 · commercial ✓ctx 262,144$0.1/$0.15 per 1M tokbase: Qwen/Qwen3.5-9B-Base
6. 06
   chronos-2@amazon⬇ 29,542,402 · flat

   time-series-forecastingapache-2.0 · commercial ✓
7. 07
   chronos-2@autogluon⬇ 11,964,163 · flat

   time-series-forecastingapache-2.0 · commercial ✓
8. 08
   gpt-oss-20b@openai⬇ 8,616,555 · flat

   chat & code genapache-2.0 · commercial ✓ctx 131,072$0.03/$0.13 per 1M tok
9. 09
   Qwen3-Embedding-0.6B@Qwen⬇ 9,771,658 · flat

   embeddingsapache-2.0 · commercial ✓base: Qwen/Qwen3-0.6B-Base
10. 10
    Qwen3-32B@Qwen⬇ 8,346,113 · flat

    chat & code genapache-2.0 · commercial ✓ctx 131,072$0.08/$0.28 per 1M tok
11. 11
    Qwen3-8B@Qwen⬇ 16,272,885 · flat

    chat & code genapache-2.0 · commercial ✓ctx 131,072$0.12/$0.45 per 1M tokbase: Qwen/Qwen3-8B-Base
12. 12
    Qwen3-0.6B@Qwen⬇ 29,699,637 · flat

    chat & code genapache-2.0 · commercial ✓base: Qwen/Qwen3-0.6B-Base
13. 13
    Qwen2.5-VL-7B-Instruct@Qwen⬇ 9,333,867 · flat

    image-text-to-textapache-2.0 · commercial ✓
14. 14
    DeepSeek-R1@deepseek-ai⬇ 9,934,359 · flat

    chat & code genmit · commercial ✓ctx 163,840$0.7/$2.5 per 1M tok
15. 15
    Kokoro-82M@hexgrad⬇ 11,958,398 · flat

    speech genapache-2.0 · commercial ✓base: yl4579/StyleTTS2-LJSpeech
16. 16
    tiny-Qwen2ForCausalLM-2.5@trl-internal-testing⬇ 16,487,039 · flat

    chat & code gen
17. 17
    chronos-bolt-small@autogluon⬇ 13,540,720 · flat

    time-series-forecastingapache-2.0 · commercial ✓
18. 18
    whisper-large-v3-turbo@openai⬇ 8,715,451 · flat

    speech→textmit · commercial ✓base: openai/whisper-large-v3
19. 19
    Llama-3.2-1B-Instruct@meta-llama⬇ 10,412,058 · flat

    chat & code genllama3.2 · commercial ✓ctx 60,000$0.03/$0.2 per 1M tok
20. 20
    Qwen2.5-1.5B-Instruct@Qwen⬇ 13,977,170 · flat

    chat & code genapache-2.0 · commercial ✓base: Qwen/Qwen2.5-1.5B