Liquid AI · First MLX build 29 May 2026
LFM2.5-8B-A1B
MLX
Text lfm1.0 Trending
A 8.5B parameter text generation model from Liquid AI, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 8.5B From Hugging Face
- Quantisation
- 4-bit LFM2.5-8B-A1B-MLX-4bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.8 GB Weights, estimated
- Downloads
- 1.9K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/LFM2.5-8B-A1B-MLX-4bit --prompt "Hello"MLX builds
3 on mlx-community| LFM2.5-8B-A1B-MLX-4bit | 4-bit | 4.8 GB | 8 GB | 1.9K |
|---|---|---|---|---|
| LFM2.5-8B-A1B-OptiQ-4bit | 4-bit | 4.8 GB | 8 GB | 446 |
| LFM2.5-8B-A1B-MLX-8bit | 8-bit | 9.0 GB | 13 GB | 118 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.