mlx-community/Macaw-OptiQ-4bit
mlx-community/Macaw-OptiQ-4bit
Built with [mlx-optiq](https://mlx-optiq.com), the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. All OptiQ quants · Docs · LFM2.5 family
An OptiQ mixed-precision quant of badtheorylabs/Macaw, an on-device Mac assistant built on LFM2.5-2.6B. 1.93 GB on disk, down from 5.2 GB at bf16.
Macaw is a tool-calling agent, so the quant is aimed at keeping tool calls well formed rather than at raw benchmark scores.
What it is
Macaw keeps its base architecture, so which layers tolerate fewer bits is unchanged. The per-layer allocation comes from LFM2.5-2.6B-OptiQ-4bit rather than a fresh sensitivity sweep: 167 of 167 layers matched, 80 kept at 8-bit and 87 at 4-bit.
Run it
pip install mlx-optiq
optiq serve --model mlx-community/Macaw-OptiQ-4bitThat gives you an OpenAI and Anthropic compatible endpoint with mixed-precision KV cache, tool-call healing and prompt caching. The base model's recommended sampling ships in generation_config.json and optiq serve applies it without any flags.
Links
- Project website: mlx-optiq.com
- All OptiQ quants: mlx-optiq.com/models
- PyPI: pypi.org/project/mlx-optiq
- Base model: badtheorylabs/Macaw
