c4ai-command-a-03-2025-8bit
mlx-community/c4ai-command-a-03-2025-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
111B
Weights (est.)
≈ 118 GB
Mac memory (est.)
192 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/c4ai-command-a-03-2025-8bit --prompt "Hello"
Details
- Base model
- CohereLabs/c4ai-command-a-03-2025 (quantized)
- Vendor
- Cohere
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- cc-by-nc-4.0
- Downloads
- 39 in the last 30 days · 562 all time · 1 likes
- Published
- 2025-03-13 · updated 2025-03-18 (1y ago)
- Languages
- en, fr, de, es, it, pt, ja, ko, zh, ar, el, fa, pl, id, cs, he, hi, nl, ro, ru, tr, uk, vi
- Tags
- cohere2
Other MLX builds of CohereLabs/c4ai-command-a-03-2025
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| c4ai-command-a-03-2025-3bit | 3-bit | ≈ 48.6 GB | 64 GB+ | 31 |
| c4ai-command-a-03-2025-4bit | 4-bit | ≈ 62.5 GB | 96 GB+ | 94 |
| c4ai-command-a-03-2025-6bit | 6-bit | ≈ 90.2 GB | 128 GB+ | 29 |
| c4ai-command-a-03-2025-8bit (this one) | 8-bit | ≈ 118 GB | 192 GB+ | 39 |
| c4ai-command-a-03-2025-bf16 | bf16 | ≈ 222 GB | 256 GB+ | 66 |
| command-a-vision-07-2025-4bit | 4-bit | — | — | 85 |