Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-6.4bpwby xpashkinπ» CPUMLXβ¬ 0β₯ 0text-generationLanguageotherlicense:otherView on Hugging Face
Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-mlx-4Bitby metalman3289π» CPUMLX~8 GB12B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
Mistral-Nemo-12B-Instruct-MLX-4bit-mlx-4Bitby metalman3289π» CPUMLX~8 GB12B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationallicense:apache-2.0View on Hugging Face
qwen3.8-27b-mlx-4bitby ownllmπ» CPUMLX~17 GB27B paramsβ¬ 0β₯ 0image-text-to-textImageapache-2.0conversationallicense:apache-2.0View on Hugging Face
phi-4-mlx-4bitby ownllmπ» CPUMLXβ¬ 0β₯ 0text-generationLanguagemitconversationallicense:mitView on Hugging Face
LFM2.5-24B-A2B-JANG_4Mby OsaurusAIπ» CPUMLX~15 GB24B paramsβ¬ 0β₯ 1text-generationLanguageapache-2.0reasoningconversationallicense:apache-2.0View on Hugging Face
LFM2.5-24B-A2B-JANG_8Mby OsaurusAIπ» CPUMLX~15 GB24B paramsβ¬ 0β₯ 1text-generationLanguageapache-2.0reasoningconversationallicense:apache-2.0View on Hugging Face
Qwen3.8-Flash-Next-MLX-Serve-8bitby ddalcuπ» CPUMLXβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit-Abliteratedby thelogicalgateπ» CPUMLX~18 GB30B paramsβ¬ 0β₯ 0text-generationLanguageopenmdw-1.1conversationallicense:openmdw-1.1View on Hugging Face
LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bitby pgmharikrishnanπ» CPUMLX~15 GB24B paramsβ¬ 0β₯ 1text-generationLanguageotherconversationallicense:otherView on Hugging Face
finch-0.1-0.8Bby topoloopπ» CPUMLX~1 GB800M paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationaldataset:topoloop/ask-maps-basiclicense:apache-2.0View on Hugging Face
Qwen3.8-Flash-Next-Uncensored-oQ4e-100K-MTP-plefp8by zviratkoπ» CPUMLXβ¬ 0β₯ 0image-text-to-textImageotherconversationallicense:otherView on Hugging Face
Voxtral-Mini-4B-Realtime-2602-MLX-8bitby flo5k5π» CPUMLX~3 GB4B paramsβ¬ 0β₯ 0automatic-speech-recognitionAudioapache-2.0license:apache-2.0View on Hugging Face
Voxtral-Mini-4B-Realtime-2602-MLX-6bitby flo5k5π» CPUMLX~3 GB4B paramsβ¬ 0β₯ 0automatic-speech-recognitionAudioapache-2.0license:apache-2.0View on Hugging Face
Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-7.1bpwby xpashkinπ» CPUMLXβ¬ 0β₯ 1text-generationLanguageotherconversationallicense:otherView on Hugging Face
LFM2.5-24B-A2B-EXL3-4bpwby 0xzknwπ» CPUMLX~15 GB24B paramsβ¬ 0β₯ 0text-generationLanguageotherconversationallicense:otherView on Hugging Face
Llama-3_3-Nemotron-Super-49B-v1_5-lecore-mlxby staccsπ» CPUMLX~30 GB49B paramsβ¬ 0β₯ 0text-generationLanguageconversationalView on Hugging Face
MiniCPM5-1B-Base-8bitby nikimoriπ» CPUMLX~1 GB1B paramsβ¬ 0β₯ 0text-generationLanguageapache-2.0conversationallicense:apache-2.0View on Hugging Face