PleIAs · First MLX build 24 Apr 2025
Pleias-RAG-350M
MLX
Text apache-2.0
A 353M parameter text generation model from PleIAs, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 353M From Hugging Face
- Quantisation
- 8-bit Pleias-RAG-350M-8-bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 376 MB Weights, estimated
- Downloads
- 36 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 8-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/Pleias-RAG-350M-8-bit --prompt "Hello"MLX builds
4 on mlx-community| Pleias-RAG-350M-4-bit | 4-bit | 199 MB | 3 GB | 28 |
|---|---|---|---|---|
| Pleias-RAG-350M-6-bit | 6-bit | 287 MB | 3 GB | 29 |
| Pleias-RAG-350M-8-bit | 8-bit | 376 MB | 3 GB | 36 |
| Pleias-RAG-350M-bf16 | bf16 | 707 MB | 3 GB | 20 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.