models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
gemma-3n-E4B-it-MLX-8bitwhisper-large-v3-turbo-8bitwhisper-tiny.en-8bitnemotron-3.5-asr-streaming-0.6b-8bitMiMo-V2.5-ASR-MLX-8bitgemma-3n-E2B-it-MLX-8bitcohere-transcribe-03-2026-mlx-8bitwhisper-large-v3-8bitbelle-whisper-large-v3-turbo-zh-8bitVibeVoice-ASR-8bitmlx-MOSS-Transcribe-Diarize-8bitHuihui-gemma-3n-E4B-it-abliterated-lm-8bitparakeet-tdt-0.6b-v3-mlx-8bitNemotron-3.5-ASR-Streaming-0.6B-MLX-8bitbengali-whisper-medium-mlx-8bitcohere-transcribe-arabic-07-2026-MLX-8bitgemma-3n-E4B-it-mlx-8BitMOSS-Transcribe-Diarize-MLX-8bitVoxtral-Small-24B-2507-8bit-dense-encoderGLM-ASR-Nano-2512-8bitcohere-transcribe-mlx-8bitnemotron-3.5-asr-streaming-0.6b-8bitFun-ASR-Nano-2512-8bitMOSS-Transcribe-Diarize-MLX-8bitnemotron-speech-streaming-en-0.6b-mlx-8bitQwen3-ASR-1.7B-MLX-8bitwhisper-small-8bitwhisper-small-asr-8bitVoxtral-Mini-3B-2507-8bit-dense-encoderbelle-whisper-large-v3-zh-8bit