6-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 19.2 GB
Mac memory (est.)
24 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/Arcee-Blitz-6bit --prompt "Hello"
Details
- Base model
- arcee-ai/Arcee-Blitz (quantized)
- Vendor
- arcee-ai
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 27 in the last 30 days · 204 all time · 0 likes
- Published
- 2025-02-24 · updated 2025-06-03 (1y ago)
- Tags
- mistral
Other MLX builds of arcee-ai/Arcee-Blitz
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Arcee-Blitz-4bit | 4-bit | ≈ 13.3 GB | 24 GB+ | 54 |
| Arcee-Blitz-6bit (this one) | 6-bit | ≈ 19.2 GB | 24 GB+ | 27 |
| Arcee-Blitz-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 27 |