bf16 Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 47.1 GB
Mac memory (est.)
64 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-bf16 --prompt "Hello"
Details
- Base model
- TheDrummer/Cydonia-24B-v3 (finetune)
- Vendor
- TheDrummer
- Task
- Text generation
- Quantisation
- bf16
- Licence
- other
- Downloads
- 39 in the last 30 days · 207 all time · 0 likes
- Published
- 2025-06-04 · updated 2025-06-04 (1y ago)
- Tags
- mistral
Other MLX builds of TheDrummer/Cydonia-24B-v3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Cydonia-24B-v3-4bit | 4-bit | ≈ 13.3 GB | 24 GB+ | 114 |
| Cydonia-24B-v3-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 35 |
| Cydonia-24B-v3-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 28 |
| Cydonia-24B-v3-bf16 (this one) | bf16 | ≈ 47.1 GB | 64 GB+ | 39 |