MLX Community · First MLX build 5 Sept 2025
lille-130m-instruct
MLX
Text apache-2.0
A 127M parameter text generation model, with 4 MLX builds, from 6-bit to fp16.
- Parameters
- 127M From Hugging Face
- Quantisation
- bf16 lille-130m-instruct-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 254 MB Weights, estimated
- Downloads
- 120 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
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/lille-130m-instruct-bf16 --prompt "Hello"MLX builds
4 on mlx-community| lille-130m-instruct-6bit | 6-bit | 103 MB | 3 GB | 30 |
|---|---|---|---|---|
| lille-130m-instruct-8bit | 8-bit | 135 MB | 3 GB | 24 |
| lille-130m-instruct-bf16 | bf16 | 254 MB | 3 GB | 120 |
| lille-130m-instruct-fp16 | fp16 | 509 MB | 3 GB | 23 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.