NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI
PyPI, #5305 most downloaded on PyPI
LLMs with MLX and the Hugging Face Hub
Latest stable
0.32.2
Last release 1 months ago
16 Oct 2026
Ships unpredictably
gaps range from 2 weeks to 5 months
Some releases are documented
notes for 25 of the last 60 stable releases
1 version withdrawn
withdrawn after publishing
3 years old
99 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Fix attention value scaling in MiMo-V2-Flash by @ricky-chaoju in https://github.com/ml-explore/mlx-lm/pull/1971
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.32.1...v0.32.2
fix muse template by @nastya236 in https://github.com/ml-explore/mlx-lm/pull/1977
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Co-authored-by: michalk8 46717574+michalk8@users.noreply.github.com
Assisted-by: Codex:GPT-5.6
Co-authored-by: michalk8 46717574+michalk8@users.noreply.github.com
meta-models/Muse-Spark-Open-816B-A42B-NVFP4 by @nastya236 @michalk8 in https://github.com/ml-explore/mlx-lm/pull/1976Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.32.0...v0.31.4
Thread local generation stream to accompany MLX v0.31.2
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.31.2...v0.31.3
Caching system prompt and user messages for non-trimmable caches
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.31.0...v0.31.2
Fix CompletionsDataset mask_prompt crash
Fix CompletionsDataset mask_prompt crash (#967)
Fix save/load of CacheList by @angeloskath in https://github.com/ml-explore/mlx-lm/pull/886
--prefill-step-size as cmd line argument for speed/memory usage trade-off by @Abioy in https://github.com/ml-explore/mlx-lm/pull/943convert() uses incorrect defaults for quantization mode by @spicyneuron in https://github.com/ml-explore/mlx-lm/pull/935Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.30.7...v0.31.0
Fix Kimi Linear by @kernelpool in https://github.com/ml-explore/mlx-lm/pull/853
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.30.6...v0.30.7
Transformers v5 by @awni in https://github.com/ml-explore/mlx-lm/pull/811
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.30.5...v0.30.6
import logging as it throws no logging error in place of actual error by @Maanas-Verma in https://github.com/ml-explore/mlx-lm/pull/778
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.30.4...v0.30.5
Add AWQ/GPTQ weight transformation utilities by @ericcurtin in https://github.com/ml-explore/mlx-lm/pull/730
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.30.2...v0.30.4
Fix mlx-lm release by @awni in https://github.com/ml-explore/mlx-lm/pull/733
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.30.1...v0.30.2
fix: server busy-waiting during idle request polling by @zenyr in https://github.com/ml-explore/mlx-lm/pull/674
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.29.0...v0.30.0
Nothing published for this version
version by @awni in https://github.com/ml-explore/mlx-lm/pull/559
load_adapters that broke adapter loading by @jyork03 in https://github.com/ml-explore/mlx-lm/pull/583Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.28.3...v0.28.4
Removing the deprecated wandb params by @Goekdeniz-Guelmez in https://github.com/ml-explore/mlx-lm/pull/524
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.28.2...v0.28.3
fix bailing moe by @awni in https://github.com/ml-explore/mlx-lm/pull/514
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.28.1...v0.28.2
Fix quant predicate by @awni in https://github.com/ml-explore/mlx-lm/pull/485
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.28.0...v0.28.1
Allow fp8 by @awni in https://github.com/ml-explore/mlx-lm/pull/431
TypeError: Model.__call__() got an unexpected keyword argument 'mask' for qwen2_vl, mistral3 by @neilmehta24 in https://github.com/ml-explore/mlx-lm/pull/464Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.27.1...v0.28.0
Fix mlx_lm.perplexity seed w/ np.random.seed to ensure determinism across runs by @N8python in https://github.com/ml-explore/mlx-lm/pull/415
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.27.0...v0.27.1
Add mlx_lm.perplexity by @N8python in https://github.com/ml-explore/mlx-lm/pull/397
mlx_lm.perplexity by @N8python in https://github.com/ml-explore/mlx-lm/pull/397Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.26.4...v0.27.0
Revert symmetric kl by @awni in https://github.com/ml-explore/mlx-lm/pull/359
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.26.3...v0.26.4
Resolve streaming last token error and correct total token usage by @zenyr in https://github.com/ml-explore/mlx-lm/pull/342
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.26.2...v0.26.3
chore: fix gemma3n intermediate_size config by @mzbac in https://github.com/ml-explore/mlx-lm/pull/332
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.26.1...v0.26.2
Add dsv3 for lora by @awni in https://github.com/ml-explore/mlx-lm/pull/284
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.26.0...v0.26.1
fix dynamic quant for bias by @awni in https://github.com/ml-explore/mlx-lm/pull/216
IndexError in NaiveStreamingDetokenizer by @Muhtasham in https://github.com/ml-explore/mlx-lm/pull/253Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.25.1...v0.26.0
Nothing published for this version
Nothing published for this version
Add input_embeddings input to generate_step, Gemma 3, Qwen 2 by @mattjcly in https://github.com/ml-explore/mlx-lm/pull/179
Full Changelog: https://github.com/ml-explore/mlx-lm/compare/v0.24.1...v0.25.1
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.