MLX Community · First MLX build 28 Jun 2024
TinyMistral-248M
MLX
Text apache-2.0
A 248M parameter text generation model, with 2 MLX builds, from 4-bit to 8-bit.
- Parameters
- 248M From Hugging Face
- Quantisation
- 4-bit TinyMistral-248M-4bits
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 140 MB Weights, estimated
- Downloads
- 92 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/TinyMistral-248M-4bits --prompt "Hello"MLX builds
2 on mlx-community| TinyMistral-248M-4bits | 4-bit | 140 MB | 3 GB | 92 |
|---|---|---|---|---|
| TinyMistral-248M-8bits | 8-bit | 264 MB | 3 GB | 65 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.