Liquid AI · First MLX build 7 Jan 2026
LFM2-2.6B-Transcript
MLX
Text lfm1.0
A 2.6B parameter text generation model from Liquid AI, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 2.6B From Hugging Face
- Quantisation
- 4-bit LFM2-2.6B-Transcript-4bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.4 GB Weights, estimated
- Downloads
- 144 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 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/LFM2-2.6B-Transcript-4bit --prompt "Hello"MLX builds
5 on mlx-community| LFM2-2.6B-Transcript-4bit | 4-bit | 1.4 GB | 4 GB | 144 |
|---|---|---|---|---|
| LFM2-2.6B-Transcript-5bit | 5-bit | 1.8 GB | 4 GB | 32 |
| LFM2-2.6B-Transcript-6bit | 6-bit | 2.1 GB | 5 GB | 31 |
| LFM2-2.6B-Transcript-8bit | 8-bit | 2.7 GB | 6 GB | 40 |
| LFM2-2.6B-Transcript-bf16 | bf16 | 5.1 GB | 8 GB | 22 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.