8-bit Open on Hugging Face
Parameters
353M
Weights (est.)
≈ 376 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Pleias-RAG-350M-8-bit --prompt "Hello"
Details
- Base model
- PleIAs/Pleias-RAG-350M (quantized)
- Vendor
- PleIAs
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 34 in the last 30 days · 633 all time · 1 likes
- Published
- 2025-04-24 · updated 2025-04-24 (1y ago)
- Languages
- en, fr, it, de, es
- Tags
- llama
Other MLX builds of PleIAs/Pleias-RAG-350M
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Pleias-RAG-350M-4-bit | 4-bit | ≈ 199 MB | 8 GB+ | 28 |
| Pleias-RAG-350M-6-bit | 6-bit | ≈ 287 MB | 8 GB+ | 29 |
| Pleias-RAG-350M-8-bit (this one) | 8-bit | ≈ 376 MB | 8 GB+ | 34 |
| Pleias-RAG-350M-bf16 | bf16 | ≈ 707 MB | 8 GB+ | 20 |