Downloads · 30 days
10
11% of all-time downloads
LFM2-8B-A1B-4bit
ekryski/LFM2-8B-A1B-4bit
LFM2-8B-A1B-4bit is a machine learning model from ekryski. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
4-bit affine quantization of LiquidAI/LFM2-8B-A1B, produced with FFAI 0.1.0's ffai convert (mlx-affine format, groupsize=64).
All-time downloads
87
Public
Parameters
8.3B
4.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 GB · 100%
Parameter types
How the weights are stored.
U328.2B · 98%
Base models
Model card
From the Hugging Face model README
LFM2-8B-A1B-4bit
4-bit affine quantization of LiquidAI/LFM2-8B-A1B, produced with FFAI 0.1.0's ffai convert (mlx-affine format, group_size=64).
Conversion
ffai convert LiquidAI/LFM2-8B-A1B --bits 4 \
--upload-repo ekryski/LFM2-8B-A1B-4bit
See also
- FFAI — fast Apple Silicon LLM inference.
Model.load("ekryski/LFM2-8B-A1B-4bit")runs this checkpoint end-to-end. - FFAI quickstart
- FFAI quantization docs
- Library
- mlx
- Type
- lfm2_moe
- License
- apache-2.0
- Languages
- en
- Created
- May 30, 2026
- Updated
- May 30, 2026