Skip to content

All on-device models

Text generation models for iPhone and Mac (Core ML & MLX)

842 models for this task are tagged Core ML or MLX on Hugging Face, or come from Apple: 74 Core ML, 752 MLX and 16 other Apple models. The table lists the most downloaded in the last 30 days.

Last updated 2026-11-02 (UTC).

Showing 100 of 100.

ModelSizeDownloads (30 days)
distilbert/distilgpt2Core ML3.2 GB1.5M
prism-ml/Ternary-Bonsai-27B-mlx-2bitMLXfrom Qwen/Qwen3.6-27B8.5 GB985K
prism-ml/Bonsai-27B-mlx-1bitMLXfrom Qwen/Qwen3.6-27B5.2 GB976K
rapid-mlx/Ling-3.0-tiny-MLX-4bitMLXfrom inclusionAI/Ling-3.0-tiny4.5 GB392K
ornith-ai/Ornith-1.5-35B-A3B-MLXMLX69.3 GB344K
ornith-ai/Ornith-1.5-9B-MLX-8bitMLX9.5 GB313K
ornith-ai/Ornith-1.5-9B-MLXMLX17.9 GB313K
mlx-community/Qwen2.5-Coder-7B-Instruct-4bitMLXfrom Qwen/Qwen2.5-Coder-7B4.3 GB259K
ornith-ai/Ornith-1.5-9B-MLX-4bitMLX5.1 GB255K
NexVeridian/Qwen3-Coder-Next-8bitMLXfrom Qwen/Qwen3-Coder-Next84.7 GB225K
ornith-ai/Ornith-1.5-9B-MLX-6bitMLX7.3 GB209K
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bitMLXfrom deepseek-ai/DeepSeek-R1-0528-Qwen3-8B4.6 GB198K
ornith-ai/Ornith-1.5-35B-A3B-MLX-8bitMLX36.9 GB185K
ornith-ai/Ornith-1.5-35B-A3B-MLX-4bitMLX19.5 GB176K
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bitMLXfrom deepseek-ai/DeepSeek-R1-0528-Qwen3-8B8.7 GB171K
mlx-community/gpt-oss-20b-MXFP4-Q8MLXfrom openai/gpt-oss-20b12.1 GB160K
ornith-ai/Ornith-1.5-35B-A3B-MLX-6bitMLX28.2 GB155K
lmstudio-community/GLM-4.7-Flash-MLX-8bitMLXfrom zai-org/GLM-4.7-Flash31.8 GB154K
lmstudio-community/GLM-4.7-Flash-MLX-6bitMLXfrom zai-org/GLM-4.7-Flash24.4 GB144K
lmstudio-community/LFM2-24B-A2B-MLX-4bitMLXfrom LiquidAI/LFM2-24B-A2B13.4 GB136K
lmstudio-community/LFM2-24B-A2B-MLX-5bitMLXfrom LiquidAI/LFM2-24B-A2B16.4 GB134K
lmstudio-community/LFM2-24B-A2B-MLX-8bitMLXfrom LiquidAI/LFM2-24B-A2B25.3 GB134K
lmstudio-community/LFM2-24B-A2B-MLX-6bitMLXfrom LiquidAI/LFM2-24B-A2B19.4 GB134K
mlx-community/Kimi-K2.5MLXfrom moonshotai/Kimi-K2.5658 GB110K
lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-4bitMLXfrom Qwen/Qwen3-Coder-30B-A3B-Instruct17.2 GB87.5K
Jackrong/MLX-Qwopus3.5-9B-v3-4bitMLXfrom Jackrong/Qwopus3.5-9B-v35.1 GB81.2K
lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-5bitMLXfrom Qwen/Qwen3-Coder-30B-A3B-Instruct21 GB74.7K
lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bitMLXfrom Qwen/Qwen3-Coder-30B-A3B-Instruct32.5 GB74.2K
lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-6bitMLXfrom Qwen/Qwen3-Coder-30B-A3B-Instruct24.8 GB73.1K
lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bitMLXfrom Qwen/Qwen2.5-Coder-14B-Instruct8.3 GB72.8K
mlx-community/Qwen3-4B-Instruct-2507-4bitMLXfrom Qwen/Qwen3-4B-Instruct-25072.3 GB71.3K
lmstudio-community/LFM2.5-1.2B-Instruct-MLX-8bitMLXfrom LiquidAI/LFM2.5-1.2B-Instruct1.2 GB56K
lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-8bitMLXfrom Qwen/Qwen2.5-Coder-14B-Instruct15.7 GB55.1K
lmstudio-community/LFM2.5-1.2B-Instruct-MLX-4bitMLXfrom LiquidAI/LFM2.5-1.2B-Instruct663 MB55.1K
lmstudio-community/LFM2.5-1.2B-Instruct-MLX-6bitMLXfrom LiquidAI/LFM2.5-1.2B-Instruct956 MB54.8K
mlx-community/Qwen3-0.6B-8bitMLXfrom Qwen/Qwen3-0.6B649 MB50.8K
mlx-community/Qwen2.5-0.5B-Instruct-4bitMLXfrom Qwen/Qwen2.5-0.5B290 MB43.9K
mlx-community/Qwen3-0.6B-4bitMLXfrom Qwen/Qwen3-0.6B351 MB42.8K
lmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-4bitMLXfrom Qwen/Qwen2.5-Coder-32B-Instruct18.4 GB39K
lmstudio-community/Qwen3-14B-MLX-4bitMLXfrom Qwen/Qwen3-14B8.3 GB38.8K
lmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-8bitMLXfrom Qwen/Qwen2.5-Coder-32B-Instruct34.8 GB35.9K
mlx-community/Qwen3-8B-4bitMLXfrom Qwen/Qwen3-8B4.6 GB33.5K
lmstudio-community/Qwen3-14B-MLX-8bitMLXfrom Qwen/Qwen3-14B15.7 GB33.2K
mlx-community/Llama-3.2-3B-Instruct-4bitMLXfrom mlx-community/Llama-3.2-3B-Instruct1.8 GB32.9K
lmstudio-community/Qwen3-4B-Instruct-2507-MLX-4bitMLXfrom Qwen/Qwen3-4B-Instruct-25072.3 GB32.8K
mlx-community/Qwen3-Embedding-0.6B-4bit-DWQMLXfrom Qwen/Qwen3-Embedding-0.6B351 MB32.4K
tiiuae/falcon-7b-instructCore ML56.6 GB32.1K
mlx-community/Llama-3.2-1B-Instruct-4bitMLXfrom mlx-community/Llama-3.2-1B-Instruct-bf16713 MB31.9K
lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitMLXfrom nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF1617.8 GB30.6K
lmstudio-community/Qwen3-4B-Instruct-2507-MLX-8bitMLXfrom Qwen/Qwen3-4B-Instruct-25074.3 GB30.6K
desert-ant-labs/titleMLX294 MB30.6K
lmstudio-community/Qwen3-4B-Instruct-2507-MLX-6bitMLXfrom Qwen/Qwen3-4B-Instruct-25073.3 GB30.4K
lmstudio-community/Qwen3-4B-Instruct-2507-MLX-5bitMLXfrom Qwen/Qwen3-4B-Instruct-25072.8 GB30.3K
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-4bitMLXfrom Qwen/Qwen3-4B-Thinking-25072.3 GB27.9K
TensorFold/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bitMLXfrom nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF1618.5 GB27.6K
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-8bitMLXfrom Qwen/Qwen3-4B-Thinking-25074.3 GB27.4K
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-6bitMLXfrom Qwen/Qwen3-4B-Thinking-25073.3 GB27.2K
mlx-community/Qwen3-4B-4bitMLXfrom Qwen/Qwen3-4B2.3 GB27.1K
prism-ml/Ternary-Bonsai-2-27B-mlx-2bitMLXfrom Qwen/Qwen3.8-27B8.6 GB27K
Youssofal/Qwen3.8-27B-MTPLX-Optimized-SpeedMLXfrom Qwen/Qwen3.8-27B20.7 GB27K
lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bitMLXfrom nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF1633.6 GB27K
lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitMLXfrom nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF1625.7 GB26.6K
lmstudio-community/Qwen3-8B-MLX-8bitMLXfrom Qwen/Qwen3-8B8.7 GB26.4K
lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitMLXfrom nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF1621.7 GB26.4K
lmstudio-community/Qwen3-8B-MLX-4bitMLXfrom Qwen/Qwen3-8B4.6 GB26.2K
lmstudio-community/Phi-4-mini-reasoning-MLX-4bitMLXfrom microsoft/Phi-4-mini-reasoning2.2 GB25.6K
lmstudio-community/gpt-oss-120b-MLX-8bitMLXfrom openai/gpt-oss-120b124 GB25.4K
mlx-community/gemma-2-9b-it-4bitMLX5.2 GB22.5K
mlx-community/gemma-3-1b-it-qat-4bitMLXfrom google/gemma-3-1b-it772 MB21.3K
lmstudio-community/MiniMax-M2.5-MLX-8bitMLXfrom MiniMaxAI/MiniMax-M2.5243 GB19.7K
mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bitMLXfrom Qwen/Qwen3-Coder-30B-A3B-Instruct17.2 GB18.9K
lmstudio-community/Seed-OSS-36B-Instruct-MLX-8bitMLXfrom ByteDance-Seed/Seed-OSS-36B-Instruct38.4 GB18.3K
lmstudio-community/Seed-OSS-36B-Instruct-MLX-4bitMLXfrom ByteDance-Seed/Seed-OSS-36B-Instruct20.3 GB17.6K
lmstudio-community/Seed-OSS-36B-Instruct-MLX-5bitMLXfrom ByteDance-Seed/Seed-OSS-36B-Instruct24.9 GB17.4K
lmstudio-community/Seed-OSS-36B-Instruct-MLX-6bitMLXfrom ByteDance-Seed/Seed-OSS-36B-Instruct29.4 GB17.4K
lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-4bitMLXfrom Qwen/Qwen3-30B-A3B-Instruct-250717.2 GB16.6K
lmstudio-community/Qwen3-1.7B-MLX-8bitMLXfrom Qwen/Qwen3-1.7B1.8 GB15.7K
lmstudio-community/Qwen3-1.7B-MLX-4bitMLXfrom Qwen/Qwen3-1.7B984 MB15.7K
mlx-community/Qwen3-1.7B-4bitMLXfrom Qwen/Qwen3-1.7B984 MB15.3K
lmstudio-community/Qwen3-1.7B-MLX-bf16MLXfrom Qwen/Qwen3-1.7B3.5 GB15.3K
lmstudio-community/MiniMax-M2.5-MLX-6bitMLXfrom MiniMaxAI/MiniMax-M2.5186 GB15.2K
lmstudio-community/MiniMax-M2.5-MLX-4bitMLXfrom MiniMaxAI/MiniMax-M2.5129 GB15.1K
mlx-community/Qwen3-235B-A22B-Thinking-2507-4bitMLXfrom Qwen/Qwen3-235B-A22B-Thinking-2507132 GB15.1K
lmstudio-community/Qwen2.5-Coder-7B-Instruct-MLX-4bitMLXfrom Qwen/Qwen2.5-Coder-7B-Instruct4.3 GB15.1K
Jundot/DeepSeek-V4-Flash-0731-oQ4e-mtpMLXfrom deepseek-ai/DeepSeek-V4-Flash-0731166 GB14.9K
lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-8bitMLXfrom Qwen/Qwen3-30B-A3B-Instruct-250732.5 GB14.9K
lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-6bitMLXfrom Qwen/Qwen3-30B-A3B-Instruct-250724.8 GB14.7K
lmstudio-community/Phi-4-reasoning-plus-MLX-4bitMLXfrom microsoft/Phi-4-reasoning-plus8.3 GB14.3K
RecursiveSI/flint-int4MLX22.6 GB14.2K
mlx-community/Qwen2.5-7B-Instruct-4bitMLXfrom Qwen/Qwen2.5-7B4.3 GB14K
lmstudio-community/LFM2-1.2B-MLX-8bitMLXfrom LiquidAI/LFM2-1.2B1.2 GB13.8K
mlx-community/Qwen1.5-0.5B-Chat-4bitMLX273 MB13.8K
lmstudio-community/LFM2-1.2B-MLX-bf16MLXfrom LiquidAI/LFM2-1.2B2.3 GB13.8K
lmstudio-community/ERNIE-4.5-21B-A3B-MLX-4bitMLXfrom baidu/ERNIE-4.5-21B-A3B-PT12.3 GB13.4K
lmstudio-community/ERNIE-4.5-21B-A3B-MLX-6bitMLXfrom baidu/ERNIE-4.5-21B-A3B-PT17.7 GB13.1K
lmstudio-community/ERNIE-4.5-21B-A3B-MLX-8bitMLXfrom baidu/ERNIE-4.5-21B-A3B-PT23.2 GB13.1K
lmstudio-community/Qwen3-4B-MLX-4bitMLXfrom Qwen/Qwen3-4B2.3 GB13.1K
mlx-community/Qwen2.5-3B-Instruct-4bitMLXfrom Qwen/Qwen2.5-3B1.7 GB12.7K
lmstudio-community/Qwen3-4B-MLX-8bitMLXfrom Qwen/Qwen3-4B4.3 GB12.6K
apple/FastVLM-0.5BApple, other format1.5 GB11.6K

Reading the table

  • Downloads are Hugging Face's count for the last 30 days, not all time. Hugging Face counts requests for a model's main file, so one install can count more than once.
  • Size is the total of the repo's current files on Hugging Face, in the sizes it shows (1 GB = 1,000 MB). Some repos hold several variants of a model, so it can be larger than the one download you need; a dash means it has not been measured yet.
  • Trending is Hugging Face's own score for recent attention. "from" under a name is the model it was made from.
  • Parameters is the parameter count in the model files. A count marked * comes from the model's name (such as 27B) instead: the files gave none, or a much smaller one, as packed low-bit files can.
  • Quantization is read from the model's tags and name, not checked against the files.

Before you use one

The list comes from Hugging Face's public API and is updated daily. We don't test each model. Check the license and read the model card before you ship one in an app: some licenses limit commercial use, and "other" means the terms are on the model card. Models whose names or tags point at adult or safety-removed content are left out, and so are gated models that need a Hugging Face sign-in to download.