Mlx Community LLM Models

Mistral Small 24 B Instruct 2501 4bit

Deep Seek R1 3bit

Qwen2.5 V L 7 B Instruct 8bit

Deep Seek R1 Distill Qwen 7 B 4bit

Deep Seek R1 Distill Llama 8 B 4bit

whisper large v3 mlx

mlx_bark

llava v1.6 mistral 7b 4bit

Deep Seek V3 4bit

Deep Seek R1 Distill Qwen 1.5 B 4bit

Deep Seek R1 Distill Qwen 7 B bf16

Deep Seek R1 Distill Qwen 14 B 3bit

Deep Seek R1 Distill Llama 70 B 8bit

Deep Seek R1 Distill Llama 70 B

Deep Seek R1 Distill Qwen 32 B 4bit

Deep Seek R1 Distill Qwen 32 B Japanese 4bit

Qwen2.5 V L 3 B Instruct 8bit

Qwen2.5 V L 7 B Instruct 6bit

Qwen2.5 V L 72 B Instruct 4bit

Mistral Small 24 B Instruct 2501 bf16

jinaai Reader L M v2

deepseek r1 distill qwen 1.5b

phi 4 4bit

Unsloth Phi 4 4bit

Deep Seek R1 Distill Qwen 14 B 6bit

Llama 3.2 3 B Instruct 4bit

internlm3 8b instruct 4bit

Deep Seek R1 Distill Qwen 7 B 4bit mlx

Deep Seek R1 4bit

phi 4 8bit

phi 4 6bit

Qwen2.5 14 B Instruct 4bit

whisper large v3 turbo

Llama 3.3 70 B Instruct 4bit

Deep Seek V3 3bit

Deep Seek V3 3bit bf16

Meta Llama 3.1 8 B Instruct 8bit

Hermes 3 Llama 3.1 8 B 4bit

Llama 3.2 1 B Instruct M L X Tuned

miscii 14b 1028 4bit

Q V Q 72 B Preview 3bit

Q V Q 72 B Preview 4bit