Liquid AI · First MLX build 7 Oct 2025
LFM2-8B-A1B
MLX
Text lfm1.0
A 8.3B parameter text generation model from Liquid AI, with 8 MLX builds, from 3-bit to fp16.
- Parameters
- 8.3B From Hugging Face
- Quantisation
- 4-bit LFM2-8B-A1B-4bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.7 GB Weights, estimated
- Downloads
- 589 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 8 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/LFM2-8B-A1B-4bit --prompt "Hello"MLX builds
8 on mlx-community| LFM2-8B-A1B-3bit-MLX | 3-bit | 3.6 GB | 7 GB | 84 |
|---|---|---|---|---|
| LFM2-8B-A1B-4bit | 4-bit | 4.7 GB | 8 GB | 589 |
| LFM2-8B-A1B-5bit | 5-bit | 5.7 GB | 9 GB | 48 |
| LFM2-8B-A1B-6bit-MLX | 6-bit | 6.8 GB | 10 GB | 63 |
| LFM2-8B-A1B-6bit | 6-bit | 6.8 GB | 10 GB | 37 |
| LFM2-8B-A1B-8bit-MLX | 8-bit | 8.9 GB | 12 GB | 65 |
| LFM2-8B-A1B-8bit | 8-bit | 8.9 GB | 12 GB | 63 |
| LFM2-8B-A1B-fp16 | fp16 | 33.4 GB | 40 GB | 41 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.