4-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 13.3 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/Cydonia-24B-v3.1-4bit --prompt "Hello"
Details
- Base model
- TheDrummer/Cydonia-24B-v3.1 (quantized)
- Vendor
- TheDrummer
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 101 in the last 30 days · 773 all time · 1 likes
- Published
- 2025-06-25 · updated 2025-06-25 (1y ago)
- Tags
- mistral
Other MLX builds of TheDrummer/Cydonia-24B-v3.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Cydonia-24B-v3.1-4bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 101 |
| Cydonia-24B-v3.1-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 29 |
| Cydonia-24B-v3.1-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 21 |
| Cydonia-24B-v3.1-bf16 | bf16 | ≈ 47.1 GB | 64 GB+ | 25 |