| parakeet-tdt-0.6b-v2 | mlx | mlx | | 1,723,524 | nvidia/parakeet-tdt-0.6b-v2 |
| parakeet-tdt-0.6b-v3 | mlx | mlx | | 1,323,189 | nvidia/parakeet-tdt-0.6b-v3 |
| whisper-tiny | mlx | mlx | | 678,386 | openai/whisper-tiny |
| parakeet-tdt_ctc-110m | mlx | mlx | | 201,888 | nvidia/parakeet-tdt_ctc-110m |
| whisper-large-v3-turbo | mlx | mlx | | 79,712 | ivrit-ai/whisper-large-v3-turbo |
| whisper-small-mlx | mlx | mlx | | 29,012 | openai/whisper-small |
| whisper-large-v3-mlx | mlx | mlx | | 26,713 | openai/whisper-large |
| Qwen3-TTS-12Hz-0.6B-Base-4bit | mlx | mlx | | 17,493 | Qwen/Qwen3-TTS-12Hz-0.6B-Base |
| Qwen3-TTS-12Hz-1.7B-Base-bf16 | mlx | mlx | | 16,720 | Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| orpheus-3b-0.1-ft-bf16 | mlx | mlx | | 15,248 | canopylabs/orpheus-3b-0.1-ft |
| Kokoro-82M-bf16 | mlx | mlx | | 13,824 | yl4579/StyleTTS2-LJSpeech |
| gemma-3n-E2B-it-lm-4bit | mlx | mlx | | 6,432 | google/gemma-3n-E2B-it |
| whisper-base-mlx | mlx | mlx | | 5,576 | openai/whisper-base |
| Qwen3-TTS-12Hz-0.6B-Base-bf16 | mlx | mlx | | 5,356 | Qwen/Qwen3-TTS-12Hz-0.6B-Base |
| whisper-medium-mlx | mlx | mlx | | 4,602 | openai/whisper-medium |
| Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit | mlx | mlx | | 4,406 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice |
| whisper-large-v3-turbo-4bit | mlx | mlx | | 3,847 | openai/whisper-large-v3-turbo |
| Qwen3-TTS-12Hz-1.7B-Base-8bit | mlx | mlx | | 3,142 | Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| Qwen3-TTS-12Hz-0.6B-Base-8bit | mlx | mlx | | 2,694 | Qwen/Qwen3-TTS-12Hz-0.6B-Base |
| Qwen3-TTS-12Hz-1.7B-VoiceDesign-bf16 | mlx | mlx | | 2,495 | Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign |
| Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit | mlx | mlx | | 2,412 | — |
| whisper-large-v3-turbo-asr-fp16 | mlx | mlx | | 1,954 | — |
| Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit | mlx | mlx | | 1,907 | — |
| parakeet-tdt-1.1b | mlx | mlx | | 1,899 | nvidia/parakeet-tdt-1.1b |
| gemma-3n-E4B-it-lm-4bit | mlx | mlx | | 1,778 | google/gemma-3n-E4B-it |
| Qwen3-TTS-12Hz-1.7B-CustomVoice-6bit | mlx | mlx | | 1,494 | — |
| fish-audio-s2-pro-bf16 | mlx | mlx | | 1,219 | fishaudio/s2-pro |
| Qwen3-TTS-12Hz-1.7B-CustomVoice-bf16 | mlx | mlx | | 1,210 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice |
| whisper-large-v3-turbo-8bit | mlx | mlx | | 1,148 | openai/whisper-large-v3-turbo |
| Voxtral-4B-TTS-2603-mlx-4bit | mlx | mlx | | 1,097 | mistralai/Voxtral-4B-TTS-2603 |
| chatterbox-turbo-fp16 | mlx | mlx | | 1,036 | mlx-community/chatterbox-turbo-fp16 |
| VibeVoice-ASR-4bit | mlx | mlx | | 1,035 | microsoft/VibeVoice-ASR |
| chatterbox-fp16 | mlx | mlx | | 1,014 | ResembleAI/chatterbox |
| Qwen3-TTS-12Hz-1.7B-VoiceDesign-4bit | mlx | mlx | | 997 | Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign |
| Voxtral-Mini-4B-Realtime-2602-4bit | mlx | mlx | | 979 | mistralai/Voxtral-Mini-4B-Realtime-2602 |
| fish-audio-s2-pro-8bit | mlx | mlx | | 955 | fishaudio/s2-pro |
| nemotron-3.5-asr-streaming-0.6b | mlx | mlx | | 950 | nvidia/nemotron-3.5-asr-streaming-0.6b |
| Qwen3-TTS-12Hz-0.6B-CustomVoice-bf16 | mlx | mlx | | 876 | Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice |
| Kokoro-82M-4bit | mlx | mlx | | 801 | yl4579/StyleTTS2-LJSpeech |
| Soprano-80M-bf16 | mlx | mlx | | 732 | — |
| VoxCPM2-8bit | mlx | mlx | | 707 | openbmb/VoxCPM2 |
| Qwen3-TTS-12Hz-0.6B-CustomVoice-4bit | mlx | mlx | | 676 | Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice |
| whisper-large-v3-turbo-fp16 | mlx | mlx | | 666 | openai/whisper-large-v3-turbo |
| diar_streaming_sortformer_4spk-v2.1-fp16 | mlx | mlx | | 620 | nvidia/diar_streaming_sortformer_4spk-v2.1 |
| whisper-tiny.en-8bit | mlx | mlx | | 593 | openai/whisper-tiny.en |
| MiMo-V2.5-ASR-MLX-8bit | mlx | mlx | | 593 | XiaomiMiMo/MiMo-V2.5-ASR |
| Kokoro-82M-8bit | mlx | mlx | | 578 | yl4579/StyleTTS2-LJSpeech |
| Dia-1.6B | mlx | mlx | | 559 | nari-labs/Dia-1.6B |
| parakeet-tdt_ctc-0.6b-ja | mlx | mlx | | 537 | nvidia/parakeet-tdt_ctc-0.6b-ja |
| kitten-tts-nano-0.8-fp16 | mlx | mlx | | 534 | — |
| gemma-3n-E2B-it-4bit | mlx | mlx | | 512 | google/gemma-3n-E4B-it |
| csm-1b-8bit | mlx | mlx | | 471 | — |
| Qwen3-TTS-12Hz-1.7B-Base-4bit | mlx | mlx | | 467 | Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| Qwen3-TTS-12Hz-1.7B-CustomVoice-4bit | mlx | mlx | | 459 | Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice |
| svara-tts-v1 | mlx | mlx | | 438 | kenpath/svara-tts-v1 |
| Voxtral-4B-TTS-2603-mlx-bf16 | mlx | mlx | | 434 | mistralai/Voxtral-4B-TTS-2603 |
| Chatterbox-TTS-4bit | mlx | mlx | | 423 | ResembleAI/chatterbox |
| Qwen3-TTS-12Hz-1.7B-VoiceDesign-6bit | mlx | mlx | | 407 | — |
| nemotron-3.5-asr-streaming-0.6b-8bit | mlx | mlx | | 378 | nvidia/nemotron-3.5-asr-streaming-0.6b |
| Spark-TTS-0.5B-bf16 | mlx | mlx | | 361 | SparkAudio/Spark-TTS-0.5B |
| silero-vad | mlx | mlx | | 347 | freddyaboulton/silero-vad |
| Fun-CosyVoice3-0.5B-2512-fp16 | mlx | mlx | | 345 | FunAudioLLM/Fun-CosyVoice3-0.5B-2512 |
| Llama-OuteTTS-1.0-1B-4bit | mlx | mlx | | 327 | OuteAI/Llama-OuteTTS-1.0-1B |
| Qwen3-TTS-12Hz-1.7B-Base-6bit | mlx | mlx | | 317 | Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| orpheus-3b-0.1-ft-4bit | mlx | mlx | | 314 | canopylabs/orpheus-3b-0.1-ft |
| MeloTTS-English-v3-MLX | mlx | mlx | | 308 | myshell-ai/MeloTTS-English-v3 |
| Voxtral-Mini-4B-Realtime-2602-fp16 | mlx | mlx | | 307 | mistralai/Voxtral-Mini-4B-Realtime-2602 |
| whisper-tiny-asr-fp16 | mlx | mlx | | 299 | — |
| VoxCPM2-4bit | mlx | mlx | | 289 | openbmb/VoxCPM2 |
| IndexTTS-2-fp16 | mlx | mlx | | 277 | IndexTeam/IndexTTS-2 |
| chatterbox-turbo-4bit | mlx | mlx | | 275 | ResembleAI/chatterbox-turbo |
| csm-1b | mlx | mlx | | 268 | sesame/csm-1b |
| Chatterbox-TTS-fp16 | mlx | mlx | | 264 | ResembleAI/chatterbox |
| chatterbox-4bit | mlx | mlx | | 264 | ResembleAI/chatterbox |
| Qwen3-Omni-30B-A3B-Instruct-4bit | mlx | mlx | | 259 | Qwen/Qwen3-Omni-30B-A3B-Instruct |
| gemma-3n-E4B-it-4bit | mlx | mlx | | 248 | google/gemma-3n-E4B |
| VoxCPM2-bf16 | mlx | mlx | | 240 | openbmb/VoxCPM2 |
| index-tts2-mlx | mlx | mlx | | 231 | — |
| chatterbox-turbo-8bit | mlx | mlx | | 226 | ResembleAI/chatterbox-turbo |
| Qwen3-TTS-12Hz-0.6B-CustomVoice-6bit | mlx | mlx | | 226 | — |
| Qwen3-Omni-30B-A3B-Instruct-bf16 | mlx | mlx | | 220 | Qwen/Qwen3-Omni-30B-A3B-Instruct |
| fishaudio-s2-pro-8bit-mlx | mlx | mlx | | 214 | fishaudio/s2-pro |
| diar_sortformer_4spk-v1-fp16 | mlx | mlx | | 212 | nvidia/diar_sortformer_4spk-v1 |
| MiMo-V2.5-ASR-MLX | mlx | mlx | | 210 | XiaomiMiMo/MiMo-V2.5-ASR |
| whisper-large-v3-turbo-german-f16 | mlx | mlx | | 206 | primeline/whisper-large-v3-german |
| silero-vad-v6 | mlx | mlx | | 200 | snakers4/silero-vad |
| kimi-audio-7b | mlx | mlx | | 197 | — |
| Qwen3-TTS-12Hz-0.6B-Base-6bit | mlx | mlx | | 193 | Qwen/Qwen3-TTS-12Hz-0.6B-Base |
| parakeet-ctc-0.6b | mlx | mlx | | 193 | nvidia/parakeet-ctc-0.6b |
| Voxtral-4B-TTS-2603-mlx-6bit | mlx | mlx | | 187 | mistralai/Voxtral-4B-TTS-2603 |
| Fun-CosyVoice3-0.5B-2512-4bit | mlx | mlx | | 182 | FunAudioLLM/Fun-CosyVoice3-0.5B-2512 |
| mel-roformer-kim-vocal-2-mlx | mlx | mlx | | 181 | KimberleyJSN/melbandroformer |
| granite-speech-4.1-2b-nar-mlx | mlx | mlx | | 178 | ibm-granite/granite-speech-4.1-2b-nar |
| smart-turn-v3 | mlx | mlx | | 178 | pipecat-ai/smart-turn-v3 |
| Fun-ASR-Nano-2512-4bit | mlx | mlx | | 173 | FunAudioLLM/Fun-ASR-Nano-2512 |
| OmniVoice | mlx | mlx | | 171 | k2-fsa/OmniVoice |
| Soprano-1.1-80M-bf16 | mlx | mlx | | 169 | ekwek/Soprano-1.1-80M |
| supertonic-3-mlx | mlx | mlx | | 169 | Supertone/supertonic-3 |
| IndexTTS-1.5 | mlx | mlx | | 168 | IndexTeam/IndexTTS-1.5 |
| Soprano-1.1-80M-5bit | mlx | mlx | | 164 | ekwek/Soprano-1.1-80M |
| VibeVoice-ASR-bf16 | mlx | mlx | | 161 | microsoft/VibeVoice-ASR |
| belle-whisper-large-v3-turbo-zh-8bit | mlx | mlx | | 160 | — |
| Kokoro-82M-6bit | mlx | mlx | | 159 | yl4579/StyleTTS2-LJSpeech |
| GLM-ASR-Nano-2512-4bit | mlx | mlx | | 158 | zai-org/GLM-ASR-Nano-2512 |
| whisper-large-v3-turbo-asr-4bit | mlx | mlx | | 157 | — |
| OmniVoice-4bit | mlx | mlx | | 155 | k2-fsa/OmniVoice |
| chatterbox-8bit | mlx | mlx | | 154 | ResembleAI/chatterbox |
| OmniVoice-bfloat16 | mlx | mlx | | 154 | k2-fsa/OmniVoice |
| VibeVoice-ASR-8bit | mlx | mlx | | 154 | — |
| whisper-large-v3-turbo-asr-8bit | mlx | mlx | | 149 | — |
| Fun-CosyVoice3-0.5B-2512-8bit | mlx | mlx | | 147 | FunAudioLLM/Fun-CosyVoice3-0.5B-2512 |
| LFM2.5-Audio-1.5B-bf16 | mlx | mlx | | 147 | LiquidAI/LFM2-1.2B |
| whisper-large-v3-asr-fp16 | mlx | mlx | | 146 | — |
| Voxtral-Mini-4B-Realtime-6bit | mlx | mlx | | 144 | mistralai/Voxtral-Mini-4B-Realtime-2602 |
| gemma-3n-E4B-it-bf16 | mlx | mlx | | 142 | google/gemma-3n-E4B |
| whisper-large-v3-fp16 | mlx | mlx | | 142 | openai/whisper-large-v3 |
| Huihui-gemma-3n-E4B-it-abliterated-lm-8bit | mlx | mlx | | 137 | huihui-ai/Huihui-gemma-3n-E4B-it-abliterated |
| diar_sortformer_4spk-v1-fp32 | mlx | mlx | | 137 | nvidia/diar_sortformer_4spk-v1 |
| Fun-ASR-Nano-2512-fp16 | mlx | mlx | | 136 | FunAudioLLM/Fun-ASR-Nano-2512 |
| VibeVoice-Realtime-0.5B-4bit | mlx | mlx | | 129 | Qwen/Qwen2.5-0.5B |
| gemma-3n-E2B-it-text-4bit-dwq | mlx | mlx | | 128 | google/gemma-3n-E2B-it |
| whisper-large-v3-8bit | mlx | mlx | | 128 | openai/whisper-large-v3 |
| VibeVoice-Realtime-0.5B-fp16 | mlx | mlx | | 121 | Qwen/Qwen2.5-0.5B |
| parakeet-tdt_ctc-1.1b | mlx | mlx | | 120 | nvidia/parakeet-tdt_ctc-1.1b |
| Qwen3-Omni-30B-A3B-Instruct-8bit | mlx | mlx | | 118 | Qwen/Qwen3-Omni-30B-A3B-Instruct |
| MiMo-V2.5-ASR-MLX-4bit | mlx | mlx | | 116 | XiaomiMiMo/MiMo-V2.5-ASR |
| whisper-large-v3-4bit | mlx | mlx | | 114 | openai/whisper-large |
| Dia-1.6B-fp16 | mlx | mlx | | 113 | nari-labs/Dia-1.6B |
| higgs-audio-v2-3B-mlx-q8 | mlx | mlx | | 112 | — |
| diar_streaming_sortformer_4spk-v2.1-fp32 | mlx | mlx | | 111 | nvidia/diar_streaming_sortformer_4spk-v2.1 |
| MiMo-V2.5-ASR-MLX-fp32 | mlx | mlx | | 110 | XiaomiMiMo/MiMo-V2.5-ASR |
| MiMo-V2.5-ASR-MLX-bf16 | mlx | mlx | | 109 | XiaomiMiMo/MiMo-V2.5-ASR |
| stable-audio-3-small-music | mlx | mlx | | 108 | stabilityai/stable-audio-3-small-music |
| Confucius4-TTS-mlx-int8 | mlx | mlx | | 101 | netease-youdao/Confucius4-TTS |
| MOSS-TTS-8B-8bit | mlx | mlx | | 98 | — |
| Irodori-TTS-600M-v3-VoiceDesign-8bit | mlx | mlx | | 96 | — |
| sam-audio-large | mlx | mlx | | 95 | facebook/sam-audio-large |
| whisper-large-v3-turbo-german-f16-q4 | mlx | mlx | | 94 | — |
| stable-audio-3-small-sfx | mlx | mlx | | 92 | stabilityai/stable-audio-3-small-sfx |
| gemma-3n-E4B-it-lm-bf16 | mlx | mlx | | 89 | MuXodious/gemma-3n-E4B-it-PaperWitch-heresy |
| OmniVoice-8bit | mlx | mlx | | 86 | — |
| LFM2.5-Audio-1.5B-8bit | mlx | mlx | | 84 | — |
| pocket-tts-8bit | mlx | mlx | | 82 | — |
| Dia-1.6B-4bit | mlx | mlx | | 81 | nari-labs/Dia-1.6B |
| IndexTTS | mlx | mlx | | 80 | — |
| whisper-small-4bit | mlx | mlx | | 80 | openai/whisper-small |
| GLM-ASR-Nano-2512-8bit | mlx | mlx | | 79 | — |
| whisper-small-asr-fp16 | mlx | mlx | | 79 | — |
| Chatterbox-Turbo-TTS-4bit | mlx | mlx | | 77 | — |
| Zyphra-ZONOS2 | mlx | mlx | | 73 | — |
| Chatterbox-TTS-8bit | mlx | mlx | | 71 | — |
| orpheus-3b-0.1-ft-8bit | mlx | mlx | | 70 | — |
| kitten-tts-mini-0.8 | mlx | mlx | | 69 | — |
| gemma-3n-E2B-4bit | mlx | mlx | | 69 | MuXodious/gemma-3n-E2B-it-absolute-heresy |
| Irodori-TTS-600M-v3-VoiceDesign-fp16 | mlx | mlx | | 68 | Aratako/Irodori-TTS-600M-v3-VoiceDesign |
| mel-roformer-zfturbo-vocals-v1-mlx | mlx | mlx | | 68 | — |
| LFM2.5-Audio-1.5B-4bit | mlx | mlx | | 67 | LiquidAI/LFM2.5-Audio-1.5B |
| higgs-audio-v2-3B-mlx-q6 | mlx | mlx | | 66 | — |
| granite-speech-4.1-2b-nar-mlx-5bit | mlx | mlx | | 66 | ibm-granite/granite-speech-4.1-2b-nar |
| whisper-base-asr-fp16 | mlx | mlx | | 65 | openai/whisper-base |
| LongCat-AudioDiT-1B-bf16 | mlx | mlx | | 64 | — |
| whisper-small-asr-4bit | mlx | mlx | | 62 | — |
| chatterbox-6bit | mlx | mlx | | 59 | — |
| Ming-omni-tts-0.5B-4bit | mlx | mlx | | 59 | inclusionAI/Ming-omni-tts-0.5B |
| parakeet-rnnt-0.6b | mlx | mlx | | 59 | nvidia/parakeet-rnnt-0.6b |
| Huihui-gemma-3n-E4B-it-abliterated-lm-4bit | mlx | mlx | | 59 | huihui-ai/Huihui-gemma-3n-E4B-it-abliterated |
| sam-audio-small | mlx | mlx | | 59 | facebook/sam-audio-small |
| Fun-ASR-Nano-2512-8bit | mlx | mlx | | 58 | — |
| Fun-ASR-MLT-Nano-2512-4bit | mlx | mlx | | 58 | FunAudioLLM/Fun-ASR-MLT-Nano-2512 |
| VyvoTTS-EN-Beta-4bit | mlx | mlx | | 57 | — |
| pocket-tts-4bit | mlx | mlx | | 57 | kyutai/pocket-tts |
| CosyVoice2-0.5B-fp16 | mlx | mlx | | 55 | FunAudioLLM/CosyVoice2-0.5B |
| MeloTTS-English-MLX | mlx | mlx | | 55 | myshell-ai/MeloTTS-English-v3 |
| Ming-omni-tts-16.8B-A3B-bf16 | mlx | mlx | | 54 | inclusionAI/Ming-omni-tts-16.8B-A3B |
| Fun-ASR-MLT-Nano-2512-8bit | mlx | mlx | | 52 | — |
| sam-audio-large-fp16 | mlx | mlx | | 52 | facebook/sam-audio-large |
| VibeVoice-Realtime-0.5B-8bit | mlx | mlx | | 51 | — |
| OmniVoice-fp32 | mlx | mlx | | 51 | k2-fsa/OmniVoice |
| Huihui-gemma-3n-E4B-it-abliterated-lm-6bit | mlx | mlx | | 51 | huihui-ai/Huihui-gemma-3n-E4B-it-abliterated |
| gemma-3n-E4B-bf16 | mlx | mlx | | 50 | MuXodious/gemma-3n-E4B-it-PaperWitch-heresy |
| Chatterbox-Turbo-TTS-fp16 | mlx | mlx | | 49 | — |
| belle-whisper-large-v3-turbo-zh-fp16 | mlx | mlx | | 47 | — |
| kitten-tts-nano-0.8-5bit | mlx | mlx | | 46 | — |
| Fun-ASR-MLT-Nano-2512-fp16 | mlx | mlx | | 46 | FunAudioLLM/Fun-ASR-MLT-Nano-2512 |
| whisper-small-asr-6bit | mlx | mlx | | 46 | — |
| kitten-tts-nano-0.8 | mlx | mlx | | 45 | — |
| Zonos-v0.1-transformer-bf16 | mlx | mlx | | 45 | Zyphra/Zonos-v0.1-transformer |
| Qwen3-TTS-12Hz-0.6B-Base-5bit | mlx | mlx | | 44 | Qwen/Qwen3-TTS-12Hz-0.6B-Base |
| whisper-base-4bit | mlx | mlx | | 44 | openai/whisper-base |
| whisper-tiny-4bit | mlx | mlx | | 44 | openai/whisper-tiny |
| belle-whisper-large-v3-zh-8bit | mlx | mlx | | 44 | — |
| whisper-small-fp16 | mlx | mlx | | 43 | openai/whisper-small |
| whisper-tiny-asr-4bit | mlx | mlx | | 43 | — |
| VoxCPM1.5 | mlx | mlx | | 41 | openbmb/VoxCPM1.5 |
| Dia-1.6B-6bit | mlx | mlx | | 40 | — |
| whisper-small-asr-8bit | mlx | mlx | | 40 | — |
| Mega-ASR-bf16 | mlx | mlx | | 40 | — |
| Irodori-TTS-500M-v3-8bit | mlx | mlx | | 39 | — |
| whisper-tiny-asr-6bit | mlx | mlx | | 39 | — |
| CosyVoice2-0.5B-4bit | mlx | mlx | | 37 | FunAudioLLM/CosyVoice2-0.5B |
| Chatterbox-Turbo-TTS-8bit | mlx | mlx | | 37 | — |
| Irodori-TTS-500M-v3-fp16 | mlx | mlx | | 36 | Aratako/Irodori-TTS-500M-v3 |
| whisper-tiny-fp16 | mlx | mlx | | 35 | openai/whisper-tiny |
| SoulX-Singer-bf16 | mlx | mlx | | 35 | — |
| VoxCPM1.5-4bit | mlx | mlx | | 34 | openbmb/VoxCPM1.5 |
| Qwen3-TTS-12Hz-1.7B-CustomVoice-5bit | mlx | mlx | | 34 | — |
| Qwen3-Omni-30B-A3B-Instruct-6bit | mlx | mlx | | 34 | Qwen/Qwen3-Omni-30B-A3B-Instruct |
| whisper-large-v3-turbo-asr-6bit | mlx | mlx | | 34 | — |
| Qwen3-TTS-12Hz-1.7B-VoiceDesign-5bit | mlx | mlx | | 33 | — |
| VibeVoice-ASR-6bit | mlx | mlx | | 33 | — |
| Qwen3-Omni-30B-A3B-Instruct-5bit | mlx | mlx | | 31 | Qwen/Qwen3-Omni-30B-A3B-Instruct |
| SoulX-Singer-fp32 | mlx | mlx | | 31 | — |
| LongCat-AudioDiT-1B-4bit | mlx | mlx | | 30 | — |
| whisper-base-fp16 | mlx | mlx | | 30 | openai/whisper-base |
| belle-whisper-large-v3-zh-punct-fp16 | mlx | mlx | | 30 | — |
| Audio8-TTS-Preview-0.6b-bf16 | mlx | mlx | | 29 | — |
| whisper-tiny-8bit | mlx | mlx | | 29 | — |
| audiogen-medium-mlx | mlx | mlx | | 29 | facebook/audiogen-medium |
| sam-audio-base | mlx | mlx | | 29 | facebook/sam-audio-base |
| VoxCPM1.5-8bit | mlx | mlx | | 28 | — |
| svara-tts-v1-4bit | mlx | mlx | | 28 | kenpath/svara-tts-v1 |
| whisper-large-v3-asr-4bit | mlx | mlx | | 28 | — |
| Qwen3-TTS-12Hz-1.7B-Base-5bit | mlx | mlx | | 27 | Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| belle-whisper-large-v3-zh-fp16 | mlx | mlx | | 27 | — |
| CosyVoice2-0.5B-8bit | mlx | mlx | | 26 | — |
| VoxCPM1.5-fp16 | mlx | mlx | | 26 | openbmb/VoxCPM1.5 |
| SongGeneration-v2-medium | mlx | mlx | | 26 | — |
| SongGeneration-v2-large | mlx | mlx | | 26 | — |
| whisper-medium-fp16 | mlx | mlx | | 24 | openai/whisper-medium |
| SongGeneration-v2-large-8bit | mlx | mlx | | 24 | — |
| SoulX-Singer-8bit | mlx | mlx | | 24 | — |
| VibeVoice-Realtime-0.5B-6bit | mlx | mlx | | 23 | — |
| Soprano-80M-4bit | mlx | mlx | | 23 | — |
| SoulX-Singer | mlx | mlx | | 23 | — |
| chatterbox-turbo-mlx-q4 | mlx | mlx | | 22 | ResembleAI/chatterbox-turbo |
| VibeVoice-ASR-5bit | mlx | mlx | | 22 | — |
| SoulX-Singer-4bit | mlx | mlx | | 22 | — |
| sam-audio-small-fp16 | mlx | mlx | | 22 | facebook/sam-audio-small |
| LFM2.5-Audio-1.5B-6bit | mlx | mlx | | 22 | — |
| chatterbox-turbo-6bit | mlx | mlx | | 21 | — |
| parler-tts-mini | mlx | mlx | | 21 | parler-tts/parler-tts-mini-v1 |
| Qwen3-TTS-12Hz-0.6B-CustomVoice-5bit | mlx | mlx | | 20 | — |
| LongCat-AudioDiT-1B-8bit | mlx | mlx | | 20 | — |
| tada-tts | mlx | mlx | | 20 | — |
| Irodori-TTS-500M-v2-VoiceDesign-8bit | mlx | mlx | | 20 | — |
| whisper-small.en-asr-fp16 | mlx | mlx | | 20 | — |
| Cocktail-Fork-MRX | mlx | mlx | | 20 | — |
| svara-tts-v1-8bit | mlx | mlx | | 19 | — |
| whisper-medium-asr-fp16 | mlx | mlx | | 19 | — |
| Cocktail-Fork-MRX-adapted-eq | mlx | mlx | | 19 | — |
| kitten-tts-nano-0.8-8bit | mlx | mlx | | 18 | — |
| Irodori-TTS-500M-4bit | mlx | mlx | | 18 | Aratako/Irodori-TTS-500M-v3 |
| whisper-tiny-khmer-mlx-fp32 | mlx | mlx | | 18 | — |
| SongGeneration-v2-medium-4bit | mlx | mlx | | 18 | — |
| whisper-large-v3-asr-8bit | mlx | mlx | | 18 | — |
| whisper-large-v3-turbo-asr-5bit | mlx | mlx | | 18 | — |
| kitten-tts-micro-0.8 | mlx | mlx | | 17 | — |
| whisper-small-8bit | mlx | mlx | | 17 | — |
| whisper-tiny-asr-8bit | mlx | mlx | | 17 | — |
| whisper-small.en-asr-4bit | mlx | mlx | | 17 | — |
| belle-distil-whisper-large-v2-zh-fp16 | mlx | mlx | | 17 | — |
| belle-whisper-large-v3-zh-punct-8bit | mlx | mlx | | 17 | — |
| LongCat-AudioDiT-1B-5bit | mlx | mlx | | 16 | — |
| LongCat-AudioDiT-3.5B-8bit | mlx | mlx | | 16 | — |
| GLM-ASR-Nano-2512-5bit | mlx | mlx | | 16 | — |
| whisper-small-asr-5bit | mlx | mlx | | 16 | — |
| Mega-ASR-6bit | mlx | mlx | | 16 | — |
| Mega-ASR-8bit | mlx | mlx | | 16 | — |
| belle-distil-whisper-large-v2-zh-8bit | mlx | mlx | | 16 | — |
| SongGeneration-v2-large-4bit | mlx | mlx | | 16 | — |
| sam-audio-base-fp16 | mlx | mlx | | 16 | facebook/sam-audio-base |
| Cocktail-Fork-MRX-adapted-loudness | mlx | mlx | | 16 | — |
| maya1-4bit | mlx | mlx | | 15 | — |
| kitten-tts-nano-0.8-4bit | mlx | mlx | | 15 | — |
| kitten-tts-mini-0.8-bf16 | mlx | mlx | | 15 | — |
| LongCat-AudioDiT-3.5B-bf16 | mlx | mlx | | 15 | — |
| LongCat-AudioDiT-3.5B-mxfp8 | mlx | mlx | | 15 | — |
| LongCat-AudioDiT-3.5B-nvfp4 | mlx | mlx | | 15 | — |
| Irodori-TTS-500M-v2-VoiceDesign-fp16 | mlx | mlx | | 15 | — |
| whisper-medium-malayalam-mlx | mlx | mlx | | 15 | — |
| whisper-tiny.en-fp16 | mlx | mlx | | 15 | openai/whisper-tiny.en |
| LongCat-AudioDiT-3.5B-6bit | mlx | mlx | | 14 | — |
| GLM-ASR-Nano-2512-6bit | mlx | mlx | | 14 | — |
| whisper-large-v2-asr-fp16 | mlx | mlx | | 14 | — |
| whisper-base.en-asr-8bit | mlx | mlx | | 14 | openai/whisper-base |
| whisper-base.en-asr-fp16 | mlx | mlx | | 14 | openai/whisper-base |
| SongGeneration-v2-large-bf16 | mlx | mlx | | 14 | — |
| Cocktail-Fork-MRX-paper | mlx | mlx | | 14 | — |
| pocket-tts-6bit | mlx | mlx | | 13 | — |
| kitten-tts-micro-0.8-4bit | mlx | mlx | | 13 | — |
| LongCat-AudioDiT-1B-mxfp8 | mlx | mlx | | 13 | — |
| longcat-audiodit-3.5b-8bit-mlx | mlx | mlx | | 13 | — |
| whisper-base-8bit | mlx | mlx | | 13 | openai/whisper-base |
| whisper-base-asr-6bit | mlx | mlx | | 13 | openai/whisper-base |
| whisper-small.en-asr-8bit | mlx | mlx | | 13 | — |
| whisper-tiny.en-asr-fp16 | mlx | mlx | | 13 | — |
| SongGeneration-v2-medium-8bit | mlx | mlx | | 13 | — |
| chatterbox-5bit | mlx | mlx | | 12 | — |
| kitten-tts-micro-0.8-bf16 | mlx | mlx | | 12 | — |
| LongCat-AudioDiT-1B-6bit | mlx | mlx | | 12 | — |
| LongCat-AudioDiT-3.5B-4bit | mlx | mlx | | 12 | — |
| LongCat-AudioDiT-3.5B-5bit | mlx | mlx | | 12 | — |
| whisper-medium-4bit | mlx | mlx | | 12 | openai/whisper-medium |
| whisper-medium-asr-4bit | mlx | mlx | | 12 | — |
| whisper-tiny.en-asr-4bit | mlx | mlx | | 12 | — |
| whisper-small.en-asr-5bit | mlx | mlx | | 12 | — |
| whisper-base.en-asr-4bit | mlx | mlx | | 12 | openai/whisper-base |
| SongGeneration-v2-medium-fp32 | mlx | mlx | | 12 | — |
| SongGeneration-v2-large-fp32 | mlx | mlx | | 12 | — |
| LFM2.5-Audio-1.5B-5bit | mlx | mlx | | 12 | — |
| VoxCPM1.5-6bit | mlx | mlx | | 11 | — |
| kitten-tts-micro-0.8-fp16 | mlx | mlx | | 11 | — |
| kitten-tts-micro-0.8-5bit | mlx | mlx | | 11 | — |
| zipvoice-vietnamese | mlx | mlx | | 11 | — |
| Irodori-TTS-500M-v2-fp16 | mlx | mlx | | 11 | Aratako/Irodori-TTS-500M-v3 |
| whisper-small-khmer-mlx-fp32 | mlx | mlx | | 11 | — |
| whisper-base-asr-4bit | mlx | mlx | | 11 | openai/whisper-base |
| SongGeneration-v2-medium-bf16 | mlx | mlx | | 11 | — |
| VoxCPM1.5-5bit | mlx | mlx | | 10 | — |
| chatterbox-turbo-5bit | mlx | mlx | | 10 | — |
| kitten-tts-mini-0.8-8bit | mlx | mlx | | 10 | — |
| kitten-tts-mini-0.8-4bit | mlx | mlx | | 10 | — |
| kitten-tts-nano-0.8-bf16 | mlx | mlx | | 10 | — |
| kitten-tts-mini-0.8-fp16 | mlx | mlx | | 10 | — |
| kitten-tts-mini-0.8-5bit | mlx | mlx | | 10 | — |
| Irodori-TTS-500M-v2-VoiceDesign-4bit | mlx | mlx | | 10 | — |
| whisper-small.en-fp16 | mlx | mlx | | 10 | openai/whisper-small.en |
| whisper-base.en-fp16 | mlx | mlx | | 10 | openai/whisper-base |
| whisper-base.en-asr-6bit | mlx | mlx | | 10 | openai/whisper-base |
| belle-whisper-large-v2-zh-fp16 | mlx | mlx | | 10 | — |
| Soprano-1.1-80M-8bit | mlx | mlx | | 9 | — |
| kitten-tts-micro-0.8-8bit | mlx | mlx | | 9 | — |
| kitten-tts-nano-0.8-6bit | mlx | mlx | | 9 | — |
| LongCat-AudioDiT-1B-mxfp4 | mlx | mlx | | 9 | — |
| LongCat-AudioDiT-1B-nvfp4 | mlx | mlx | | 9 | — |
| Irodori-TTS-500M-v2-4bit | mlx | mlx | | 9 | Aratako/Irodori-TTS-500M-v3 |
| whisper-small-khmer-mlx-fp16 | mlx | mlx | | 9 | — |
| whisper-medium-8bit | mlx | mlx | | 9 | — |
| whisper-small.en-8bit | mlx | mlx | | 9 | — |
| whisper-large-v3-asr-5bit | mlx | mlx | | 9 | — |
| whisper-tiny.en-asr-8bit | mlx | mlx | | 9 | — |
| kitten-tts-mini-0.8-6bit | mlx | mlx | | 8 | — |
| LongCat-AudioDiT-3.5B-mxfp4 | mlx | mlx | | 8 | — |
| kitten-tts-mini | mlx | mlx | | 8 | — |
| whisper-medium.en-8bit | mlx | mlx | | 8 | — |
| whisper-tiny.en-4bit | mlx | mlx | | 8 | openai/whisper-tiny.en |
| whisper-large-asr-8bit | mlx | mlx | | 8 | — |
| whisper-medium-asr-8bit | mlx | mlx | | 8 | — |
| whisper-tiny-asr-5bit | mlx | mlx | | 8 | — |
| whisper-base-asr-5bit | mlx | mlx | | 8 | openai/whisper-base |
| whisper-base-asr-8bit | mlx | mlx | | 8 | openai/whisper-base |
| whisper-large-v3-asr-6bit | mlx | mlx | | 8 | — |
| VibeVoice-Realtime-0.5B-5bit | mlx | mlx | | 7 | — |
| Irodori-TTS-500M-fp16 | mlx | mlx | | 7 | Aratako/Irodori-TTS-500M-v3 |
| Irodori-TTS-500M-v2-8bit | mlx | mlx | | 7 | — |
| whisper-large-v2-asr-8bit | mlx | mlx | | 7 | — |
| whisper-medium.en-asr-6bit | mlx | mlx | | 7 | — |
| whisper-medium.en-asr-8bit | mlx | mlx | | 7 | — |
| whisper-medium.en-asr-fp16 | mlx | mlx | | 7 | — |
| whisper-tiny.en-asr-6bit | mlx | mlx | | 7 | — |
| Soprano-1.1-80M-6bit | mlx | mlx | | 6 | — |
| kitten-tts-micro-0.8-6bit | mlx | mlx | | 6 | — |
| kanitts-2 | mlx | mlx | | 6 | — |
| whisper-large-asr-fp16 | mlx | mlx | | 6 | — |
| whisper-medium.en-asr-5bit | mlx | mlx | | 6 | — |
| whisper-tiny.en-asr-5bit | mlx | mlx | | 6 | — |
| whisper-small.en-asr-6bit | mlx | mlx | | 6 | — |
| Soprano-80M-5bit | mlx | mlx | | 5 | — |
| Soprano-80M-6bit | mlx | mlx | | 5 | — |
| whisper-large-v2-asr-4bit | mlx | mlx | | 5 | — |
| whisper-large-v2-asr-6bit | mlx | mlx | | 5 | — |
| whisper-large-asr-4bit | mlx | mlx | | 5 | — |
| whisper-medium-asr-6bit | mlx | mlx | | 5 | — |
| whisper-medium.en-asr-4bit | mlx | mlx | | 5 | — |
| whisper-base.en-asr-5bit | mlx | mlx | | 5 | openai/whisper-base |
| Soprano-80M-8bit | mlx | mlx | | 4 | — |
| Irodori-TTS-500M-8bit | mlx | mlx | | 4 | — |
| whisper-large-asr-6bit | mlx | mlx | | 4 | — |
| whisper-medium-asr-5bit | mlx | mlx | | 3 | — |
| whisper-large-v2-asr-5bit | mlx | mlx | | 2 | — |
| whisper-large-asr-5bit | mlx | mlx | | 2 | — |
| mlx_bark | mlx | mlx | | 0 | — |
| MOSS-TTSD-v1.0-MLX-8bit | mlx | mlx | | 0 | — |
| MOSS-TTS-Local-Transformer-MLX-8bit | mlx | mlx | | 0 | OpenMOSS-Team/MOSS-TTS-Local-Transformer |
| supertonic-3 | mlx | mlx | | 0 | Supertone/supertonic-3 |
| chatterbox-multilingual-v3 | mlx | mlx | | 0 | — |
| LTX-2-distilled-bf16 | mlx | mlx | | 0 | — |
| LTX-2-dev-bf16 | mlx | mlx | | 0 | — |
| MOSS-SoundEffect-MLX-4bit | mlx | mlx | | 0 | — |
| MOSS-SoundEffect-v2.0-bf16 | mlx | mlx | | 0 | OpenMOSS-Team/MOSS-SoundEffect-v2.0 |
| MOSS-SoundEffect-v2.0-4bit | mlx | mlx | | 0 | OpenMOSS-Team/MOSS-SoundEffect-v2.0 |
| DeepFilterNet-mlx | mlx | mlx | | 0 | — |
| demucs-mlx | mlx | mlx | | 0 | — |
| demucs-mlx-fp16 | mlx | mlx | | 0 | — |
| htdemucs-ft-vocals-mlx | mlx | mlx | | 0 | — |