This repository hosts an 8-bit quantized MLX version of the LFM2-24B model optimized for Apple Silicon. It includes a custom chat template with system prompt and tool support. The model is designed for local inference on Macs using the MLX framework and is distributed via Hugging Face.
In the Foundation models & chat space, LFM2 24B A2B takes a focused approach. It focuses on running a 24B parameter language model efficiently on Apple Silicon devices using the MLX framework. LFM2 24B A2B is an open-source project aimed at developers. The project is open source (MIT). LFM2 24B A2B is available on the web, the command line, and API.
lmstudio-community builds and maintains LFM2 24B A2B, and it first shipped in 2023. The project is developed in the open on GitHub with 6.3k stars and 28 commits in the last 90 days. Among its 4 catalogued features are 8-bit Quantization, MLX Format, and Apple Silicon Optimized.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do