8-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 25.0 GB
Mac memory (est.)
32 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/Devstral-Small-2507-8bit --prompt "Hello"
Details
- Base model
- mlx-community/Devstral-Samll-2507-bf16 (quantized)
- Vendor
- —
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 110 in the last 30 days · 925 all time · 1 likes
- Published
- 2025-07-11 · updated 2025-07-11 (1y ago)
- Languages
- en, fr, de, es, pt, it, ja, ko, ru, zh, ar, fa, id, ms, ne, pl, ro, sr, sv, tr, uk, vi, hi, bn
- Tags
- mistral
Other MLX builds of mlx-community/Devstral-Samll-2507-bf16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Devstral-Small-2507-4bit | 4-bit | ≈ 13.3 GB | 24 GB+ | 208 |
| Devstral-Small-2507-4bit-DWQ | 4-bit DWQ | ≈ 13.3 GB | 24 GB+ | 172 |
| Devstral-Small-2507-5bit | 5-bit | ≈ 16.2 GB | 24 GB+ | 85 |
| Devstral-Small-2507-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 65 |
| Devstral-Small-2507-8bit (this one) | 8-bit | ≈ 25.0 GB | 32 GB+ | 110 |