| distilbert/distilgpt2Core ML | 3.2 GB | 88.2M | – | apache-2.0 | 155万 | 666 | 2024-02-19 |
| prism-ml/Ternary-Bonsai-27B-mlx-2bitMLX基于 Qwen/Qwen3.6-27B | 8.5 GB | 27.4B | 2-bit | apache-2.0 | 98.5万 | 220 | 2026-07-14 |
| prism-ml/Bonsai-27B-mlx-1bitMLX基于 Qwen/Qwen3.6-27B | 5.2 GB | 27B* | 1-bit | apache-2.0 | 97.6万 | 287 | 2026-07-14 |
| rapid-mlx/Ling-3.0-tiny-MLX-4bitMLX基于 inclusionAI/Ling-3.0-tiny | 4.5 GB | 7.9B | 4-bit | mit | 39.2万 | 10 | 2026-10-13 |
| ornith-ai/Ornith-1.5-35B-A3B-MLXMLX | 69.3 GB | 34.7B | – | 未注明 | 34.4万 | 65 | 2026-08-20 |
| ornith-ai/Ornith-1.5-9B-MLX-8bitMLX | 9.5 GB | 9B | 8-bit | 未注明 | 31.3万 | 28 | 2026-08-20 |
| ornith-ai/Ornith-1.5-9B-MLXMLX | 17.9 GB | 9B | – | 未注明 | 31.3万 | 34 | 2026-08-20 |
| mlx-community/Qwen2.5-Coder-7B-Instruct-4bitMLX基于 Qwen/Qwen2.5-Coder-7B | 4.3 GB | 7.6B | 4-bit | apache-2.0 | 25.9万 | 32 | 2024-09-18 |
| ornith-ai/Ornith-1.5-9B-MLX-4bitMLX | 5.1 GB | 9B | 4-bit | 未注明 | 25.5万 | 45 | 2026-08-20 |
| NexVeridian/Qwen3-Coder-Next-8bitMLX基于 Qwen/Qwen3-Coder-Next | 84.7 GB | 79.7B | 8-bit | apache-2.0 | 22.5万 | 3 | 2026-08-18 |
| ornith-ai/Ornith-1.5-9B-MLX-6bitMLX | 7.3 GB | 9B | 6-bit | 未注明 | 20.9万 | 6 | 2026-08-20 |
| lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bitMLX基于 deepseek-ai/DeepSeek-R1-0528-Qwen3-8B | 4.6 GB | 8.2B | 4-bit | mit | 19.8万 | 20 | 2025-05-29 |
| ornith-ai/Ornith-1.5-35B-A3B-MLX-8bitMLX | 36.9 GB | 34.7B | 8-bit | 未注明 | 18.5万 | 13 | 2026-08-20 |
| ornith-ai/Ornith-1.5-35B-A3B-MLX-4bitMLX | 19.5 GB | 34.7B | 4-bit | 未注明 | 17.6万 | 44 | 2026-08-20 |
| lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bitMLX基于 deepseek-ai/DeepSeek-R1-0528-Qwen3-8B | 8.7 GB | 8.2B | 8-bit | mit | 17.1万 | 25 | 2025-05-29 |
| mlx-community/gpt-oss-20b-MXFP4-Q8MLX基于 openai/gpt-oss-20b | 12.1 GB | 20.9B | 4-bit | apache-2.0 | 16万 | 100 | 2026-03-19 |
| ornith-ai/Ornith-1.5-35B-A3B-MLX-6bitMLX | 28.2 GB | 34.7B | 6-bit | 未注明 | 15.5万 | 9 | 2026-08-20 |
| lmstudio-community/GLM-4.7-Flash-MLX-8bitMLX基于 zai-org/GLM-4.7-Flash | 31.8 GB | 29.9B | 8-bit | mit | 15.4万 | 13 | 2026-01-22 |
| lmstudio-community/GLM-4.7-Flash-MLX-6bitMLX基于 zai-org/GLM-4.7-Flash | 24.4 GB | 29.9B | 6-bit | mit | 14.4万 | 10 | 2026-01-22 |
| lmstudio-community/LFM2-24B-A2B-MLX-4bitMLX基于 LiquidAI/LFM2-24B-A2B | 13.4 GB | 23.8B | 4-bit | other | 13.6万 | 4 | 2026-02-23 |
| lmstudio-community/LFM2-24B-A2B-MLX-5bitMLX基于 LiquidAI/LFM2-24B-A2B | 16.4 GB | 23.8B | 5-bit | other | 13.4万 | 3 | 2026-02-23 |
| lmstudio-community/LFM2-24B-A2B-MLX-8bitMLX基于 LiquidAI/LFM2-24B-A2B | 25.3 GB | 23.8B | 8-bit | other | 13.4万 | 2 | 2026-02-23 |
| lmstudio-community/LFM2-24B-A2B-MLX-6bitMLX基于 LiquidAI/LFM2-24B-A2B | 19.4 GB | 23.8B | 6-bit | other | 13.4万 | 3 | 2026-02-23 |
| mlx-community/Kimi-K2.5MLX基于 moonshotai/Kimi-K2.5 | 658 GB | 1026B | 4-bit | other | 11万 | 41 | 2026-01-27 |
| lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-4bitMLX基于 Qwen/Qwen3-Coder-30B-A3B-Instruct | 17.2 GB | 30.5B | 4-bit | apache-2.0 | 8.8万 | 41 | 2025-07-31 |
| Jackrong/MLX-Qwopus3.5-9B-v3-4bitMLX基于 Jackrong/Qwopus3.5-9B-v3 | 5.1 GB | 9B | 4-bit | apache-2.0 | 8.1万 | 34 | 2026-03-31 |
| lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-5bitMLX基于 Qwen/Qwen3-Coder-30B-A3B-Instruct | 21 GB | 30.5B | 5-bit | apache-2.0 | 7.5万 | 10 | 2025-08-01 |
| lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bitMLX基于 Qwen/Qwen3-Coder-30B-A3B-Instruct | 32.5 GB | 30.5B | 8-bit | apache-2.0 | 7.4万 | 26 | 2025-07-31 |
| lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-6bitMLX基于 Qwen/Qwen3-Coder-30B-A3B-Instruct | 24.8 GB | 30.5B | 6-bit | apache-2.0 | 7.3万 | 9 | 2025-07-31 |
| lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bitMLX基于 Qwen/Qwen2.5-Coder-14B-Instruct | 8.3 GB | 14.8B | 4-bit | apache-2.0 | 7.3万 | 8 | 2024-11-13 |
| mlx-community/Qwen3-4B-Instruct-2507-4bitMLX基于 Qwen/Qwen3-4B-Instruct-2507 | 2.3 GB | 4B | 4-bit | apache-2.0 | 7.1万 | 17 | 2026-01-02 |
| lmstudio-community/LFM2.5-1.2B-Instruct-MLX-8bitMLX基于 LiquidAI/LFM2.5-1.2B-Instruct | 1.2 GB | 1.2B | 8-bit | other | 5.6万 | 3 | 2026-01-07 |
| lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-8bitMLX基于 Qwen/Qwen2.5-Coder-14B-Instruct | 15.7 GB | 14.8B | 8-bit | apache-2.0 | 5.5万 | 4 | 2024-11-13 |
| lmstudio-community/LFM2.5-1.2B-Instruct-MLX-4bitMLX基于 LiquidAI/LFM2.5-1.2B-Instruct | 663 MB | 1.2B | 4-bit | other | 5.5万 | 2 | 2026-01-07 |
| lmstudio-community/LFM2.5-1.2B-Instruct-MLX-6bitMLX基于 LiquidAI/LFM2.5-1.2B-Instruct | 956 MB | 1.2B | 6-bit | other | 5.5万 | 3 | 2026-01-07 |
| mlx-community/Qwen3-0.6B-8bitMLX基于 Qwen/Qwen3-0.6B | 649 MB | 596M | 8-bit | apache-2.0 | 5.1万 | 10 | 2025-05-04 |
| mlx-community/Qwen2.5-0.5B-Instruct-4bitMLX基于 Qwen/Qwen2.5-0.5B | 290 MB | 494M | 4-bit | apache-2.0 | 4.4万 | 8 | 2024-09-18 |
| mlx-community/Qwen3-0.6B-4bitMLX基于 Qwen/Qwen3-0.6B | 351 MB | 596M | 4-bit | apache-2.0 | 4.3万 | 18 | 2025-04-28 |
| lmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-4bitMLX基于 Qwen/Qwen2.5-Coder-32B-Instruct | 18.4 GB | 32.8B | 4-bit | apache-2.0 | 3.9万 | 7 | 2024-11-13 |
| lmstudio-community/Qwen3-14B-MLX-4bitMLX基于 Qwen/Qwen3-14B | 8.3 GB | 14.8B | 4-bit | apache-2.0 | 3.9万 | 10 | 2025-04-28 |
| lmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-8bitMLX基于 Qwen/Qwen2.5-Coder-32B-Instruct | 34.8 GB | 32.8B | 8-bit | apache-2.0 | 3.6万 | 4 | 2024-11-13 |
| mlx-community/Qwen3-8B-4bitMLX基于 Qwen/Qwen3-8B | 4.6 GB | 8.2B | 4-bit | apache-2.0 | 3.3万 | 18 | 2025-04-28 |
| lmstudio-community/Qwen3-14B-MLX-8bitMLX基于 Qwen/Qwen3-14B | 15.7 GB | 14.8B | 8-bit | apache-2.0 | 3.3万 | 3 | 2025-04-28 |
| mlx-community/Llama-3.2-3B-Instruct-4bitMLX基于 mlx-community/Llama-3.2-3B-Instruct | 1.8 GB | 3.2B | 4-bit | llama3.2 | 3.3万 | 49 | 2025-03-05 |
| lmstudio-community/Qwen3-4B-Instruct-2507-MLX-4bitMLX基于 Qwen/Qwen3-4B-Instruct-2507 | 2.3 GB | 4B | 4-bit | apache-2.0 | 3.3万 | 3 | 2025-08-06 |
| mlx-community/Qwen3-Embedding-0.6B-4bit-DWQMLX基于 Qwen/Qwen3-Embedding-0.6B | 351 MB | 596M | 4-bit | apache-2.0 | 3.2万 | 15 | 2025-06-06 |
| tiiuae/falcon-7b-instructCore ML | 56.6 GB | 7.2B | – | apache-2.0 | 3.2万 | 1,042 | 2024-10-12 |
| mlx-community/Llama-3.2-1B-Instruct-4bitMLX基于 mlx-community/Llama-3.2-1B-Instruct-bf16 | 713 MB | 1.2B | 4-bit | llama3.2 | 3.2万 | 21 | 2025-03-05 |
| lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitMLX基于 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 17.8 GB | 30B* | 4-bit | other | 3.1万 | 2 | 2025-12-16 |
| lmstudio-community/Qwen3-4B-Instruct-2507-MLX-8bitMLX基于 Qwen/Qwen3-4B-Instruct-2507 | 4.3 GB | 4B | 8-bit | apache-2.0 | 3.1万 | 2 | 2025-08-06 |
| desert-ant-labs/titleMLX | 294 MB | 352M | 6-bit | other | 3.1万 | 13 | 2026-10-30 |
| lmstudio-community/Qwen3-4B-Instruct-2507-MLX-6bitMLX基于 Qwen/Qwen3-4B-Instruct-2507 | 3.3 GB | 4B | 6-bit | apache-2.0 | 3万 | 0 | 2025-08-06 |
| lmstudio-community/Qwen3-4B-Instruct-2507-MLX-5bitMLX基于 Qwen/Qwen3-4B-Instruct-2507 | 2.8 GB | 4B | 5-bit | apache-2.0 | 3万 | 0 | 2025-08-06 |
| lmstudio-community/Qwen3-4B-Thinking-2507-MLX-4bitMLX基于 Qwen/Qwen3-4B-Thinking-2507 | 2.3 GB | 4B | 4-bit | apache-2.0 | 2.8万 | 14 | 2025-08-06 |
| TensorFold/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bitMLX基于 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 18.5 GB | 31.6B | 4-bit | other | 2.8万 | 5 | 2026-10-01 |
| lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bitMLX基于 Qwen/Qwen3-4B-Thinking-2507 | 4.3 GB | 4B | 8-bit | apache-2.0 | 2.7万 | 8 | 2025-08-06 |
| lmstudio-community/Qwen3-4B-Thinking-2507-MLX-6bitMLX基于 Qwen/Qwen3-4B-Thinking-2507 | 3.3 GB | 4B | 6-bit | apache-2.0 | 2.7万 | 2 | 2025-08-06 |
| mlx-community/Qwen3-4B-4bitMLX基于 Qwen/Qwen3-4B | 2.3 GB | 4B | 4-bit | apache-2.0 | 2.7万 | 17 | 2025-04-28 |
| prism-ml/Ternary-Bonsai-2-27B-mlx-2bitMLX基于 Qwen/Qwen3.8-27B | 8.6 GB | 27.4B | 2-bit | apache-2.0 | 2.7万 | 479 | 2026-09-22 |
| Youssofal/Qwen3.8-27B-MTPLX-Optimized-SpeedMLX基于 Qwen/Qwen3.8-27B | 20.7 GB | 27.4B | 4-bit | apache-2.0 | 2.7万 | 170 | 2026-09-24 |
| lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bitMLX基于 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 33.6 GB | 30B* | 8-bit | other | 2.7万 | 3 | 2025-12-16 |
| lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitMLX基于 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 25.7 GB | 30B* | 6-bit | other | 2.7万 | 1 | 2025-12-16 |
| lmstudio-community/Qwen3-8B-MLX-8bitMLX基于 Qwen/Qwen3-8B | 8.7 GB | 8.2B | 8-bit | apache-2.0 | 2.6万 | 2 | 2025-04-28 |
| lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitMLX基于 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 21.7 GB | 30B* | 5-bit | other | 2.6万 | 0 | 2025-12-16 |
| lmstudio-community/Qwen3-8B-MLX-4bitMLX基于 Qwen/Qwen3-8B | 4.6 GB | 8.2B | 4-bit | apache-2.0 | 2.6万 | 3 | 2025-04-28 |
| lmstudio-community/Phi-4-mini-reasoning-MLX-4bitMLX基于 microsoft/Phi-4-mini-reasoning | 2.2 GB | 3.8B | 4-bit | mit | 2.6万 | 5 | 2025-05-01 |
| lmstudio-community/gpt-oss-120b-MLX-8bitMLX基于 openai/gpt-oss-120b | 124 GB | 117B | 8-bit | apache-2.0 | 2.5万 | 15 | 2025-08-06 |
| mlx-community/gemma-2-9b-it-4bitMLX | 5.2 GB | 9.2B | 4-bit | gemma | 2.3万 | 1 | 2024-11-06 |
| mlx-community/gemma-3-1b-it-qat-4bitMLX基于 google/gemma-3-1b-it | 772 MB | 1.3B | 4-bit | gemma | 2.1万 | 6 | 2025-04-18 |
| lmstudio-community/MiniMax-M2.5-MLX-8bitMLX基于 MiniMaxAI/MiniMax-M2.5 | 243 GB | 229B | 8-bit | other | 2万 | 3 | 2026-02-13 |
| mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bitMLX基于 Qwen/Qwen3-Coder-30B-A3B-Instruct | 17.2 GB | 30.5B | 4-bit | apache-2.0 | 1.9万 | 54 | 2025-08-06 |
| lmstudio-community/Seed-OSS-36B-Instruct-MLX-8bitMLX基于 ByteDance-Seed/Seed-OSS-36B-Instruct | 38.4 GB | 36.2B | 8-bit | apache-2.0 | 1.8万 | 2 | 2025-08-26 |
| lmstudio-community/Seed-OSS-36B-Instruct-MLX-4bitMLX基于 ByteDance-Seed/Seed-OSS-36B-Instruct | 20.3 GB | 36.2B | 4-bit | apache-2.0 | 1.8万 | 1 | 2025-08-26 |
| lmstudio-community/Seed-OSS-36B-Instruct-MLX-5bitMLX基于 ByteDance-Seed/Seed-OSS-36B-Instruct | 24.9 GB | 36.2B | 5-bit | apache-2.0 | 1.7万 | 1 | 2025-08-26 |
| lmstudio-community/Seed-OSS-36B-Instruct-MLX-6bitMLX基于 ByteDance-Seed/Seed-OSS-36B-Instruct | 29.4 GB | 36.2B | 6-bit | apache-2.0 | 1.7万 | 0 | 2025-08-26 |
| lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-4bitMLX基于 Qwen/Qwen3-30B-A3B-Instruct-2507 | 17.2 GB | 30.5B | 4-bit | apache-2.0 | 1.7万 | 8 | 2025-07-29 |
| lmstudio-community/Qwen3-1.7B-MLX-8bitMLX基于 Qwen/Qwen3-1.7B | 1.8 GB | 1.7B | 8-bit | apache-2.0 | 1.6万 | 1 | 2025-04-28 |
| lmstudio-community/Qwen3-1.7B-MLX-4bitMLX基于 Qwen/Qwen3-1.7B | 984 MB | 1.7B | 4-bit | apache-2.0 | 1.6万 | 0 | 2025-04-28 |
| mlx-community/Qwen3-1.7B-4bitMLX基于 Qwen/Qwen3-1.7B | 984 MB | 1.7B | 4-bit | apache-2.0 | 1.5万 | 7 | 2025-04-28 |
| lmstudio-community/Qwen3-1.7B-MLX-bf16MLX基于 Qwen/Qwen3-1.7B | 3.5 GB | 1.7B | BF16 | apache-2.0 | 1.5万 | 5 | 2025-04-28 |
| lmstudio-community/MiniMax-M2.5-MLX-6bitMLX基于 MiniMaxAI/MiniMax-M2.5 | 186 GB | 229B | 6-bit | other | 1.5万 | 0 | 2026-02-13 |
| lmstudio-community/MiniMax-M2.5-MLX-4bitMLX基于 MiniMaxAI/MiniMax-M2.5 | 129 GB | 229B | 4-bit | other | 1.5万 | 1 | 2026-02-13 |
| mlx-community/Qwen3-235B-A22B-Thinking-2507-4bitMLX基于 Qwen/Qwen3-235B-A22B-Thinking-2507 | 132 GB | 235B | 4-bit | apache-2.0 | 1.5万 | 1 | 2025-07-25 |
| lmstudio-community/Qwen2.5-Coder-7B-Instruct-MLX-4bitMLX基于 Qwen/Qwen2.5-Coder-7B-Instruct | 4.3 GB | 7.6B | 4-bit | apache-2.0 | 1.5万 | 7 | 2024-11-13 |
| Jundot/DeepSeek-V4-Flash-0731-oQ4e-mtpMLX基于 deepseek-ai/DeepSeek-V4-Flash-0731 | 166 GB | 304B | 4-bit | mit | 1.5万 | 8 | 2026-10-29 |
| lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-8bitMLX基于 Qwen/Qwen3-30B-A3B-Instruct-2507 | 32.5 GB | 30.5B | 8-bit | apache-2.0 | 1.5万 | 3 | 2025-07-29 |
| lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-6bitMLX基于 Qwen/Qwen3-30B-A3B-Instruct-2507 | 24.8 GB | 30.5B | 6-bit | apache-2.0 | 1.5万 | 0 | 2025-07-29 |
| lmstudio-community/Phi-4-reasoning-plus-MLX-4bitMLX基于 microsoft/Phi-4-reasoning-plus | 8.3 GB | 14.7B | 4-bit | mit | 1.4万 | 1 | 2025-05-01 |
| RecursiveSI/flint-int4MLX | 22.6 GB | – | INT4 | apache-2.0 | 1.4万 | 28 | 2026-10-21 |
| mlx-community/Qwen2.5-7B-Instruct-4bitMLX基于 Qwen/Qwen2.5-7B | 4.3 GB | 7.6B | 4-bit | apache-2.0 | 1.4万 | 17 | 2024-11-06 |
| lmstudio-community/LFM2-1.2B-MLX-8bitMLX基于 LiquidAI/LFM2-1.2B | 1.2 GB | 1.2B | 8-bit | other | 1.4万 | 4 | 2025-07-22 |
| mlx-community/Qwen1.5-0.5B-Chat-4bitMLX | 273 MB | 464M | 4-bit | other | 1.4万 | 4 | 2024-04-18 |
| lmstudio-community/LFM2-1.2B-MLX-bf16MLX基于 LiquidAI/LFM2-1.2B | 2.3 GB | 1.2B | BF16 | other | 1.4万 | 6 | 2025-07-22 |
| lmstudio-community/ERNIE-4.5-21B-A3B-MLX-4bitMLX基于 baidu/ERNIE-4.5-21B-A3B-PT | 12.3 GB | 21.8B | 4-bit | apache-2.0 | 1.3万 | 2 | 2025-07-10 |
| lmstudio-community/ERNIE-4.5-21B-A3B-MLX-6bitMLX基于 baidu/ERNIE-4.5-21B-A3B-PT | 17.7 GB | 21.8B | 6-bit | apache-2.0 | 1.3万 | 1 | 2025-07-10 |
| lmstudio-community/ERNIE-4.5-21B-A3B-MLX-8bitMLX基于 baidu/ERNIE-4.5-21B-A3B-PT | 23.2 GB | 21.8B | 8-bit | apache-2.0 | 1.3万 | 1 | 2025-07-10 |
| lmstudio-community/Qwen3-4B-MLX-4bitMLX基于 Qwen/Qwen3-4B | 2.3 GB | 4B | 4-bit | apache-2.0 | 1.3万 | 1 | 2025-04-28 |
| mlx-community/Qwen2.5-3B-Instruct-4bitMLX基于 Qwen/Qwen2.5-3B | 1.7 GB | 3.1B | 4-bit | other | 1.3万 | 2 | 2024-09-18 |
| lmstudio-community/Qwen3-4B-MLX-8bitMLX基于 Qwen/Qwen3-4B | 4.3 GB | 4B | 8-bit | apache-2.0 | 1.3万 | 0 | 2025-04-28 |
| apple/FastVLM-0.5BApple,其他格式 | 1.5 GB | 759M | – | apple-amlr | 1.2万 | 408 | 2025-09-03 |