AlphaMonarch-7B-mlx-4bit
mlx-community/AlphaMonarch-7B-mlx-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
7.2B
Weights (est.)
≈ 4.3 GB
Mac memory (est.)
8 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.
Details
- Base model
- mlabonne/NeuralMonarch-7B (finetune)
- Vendor
- mlabonne
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- cc-by-nc-4.0
- Downloads
- 24 in the last 30 days · 328 all time · 3 likes
- Published
- 2024-02-19 · updated 2024-02-19 (2y ago)
- Languages
- en
- Tags
- mistral, merge, lazymergekit, rlhf
Other MLX builds of mlabonne/NeuralMonarch-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| AlphaMonarch-7B-mlx | — | ≈ 4.3 GB | 8 GB+ | 31 |
| AlphaMonarch-7B-mlx-4bit (this one) | 4-bit | ≈ 4.3 GB | 8 GB+ | 24 |