4-bit Open on Hugging Face
Parameters
15B
Weights (est.)
≈ 8.3 GB
Mac memory (est.)
16 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/Lamarck-14B-v0.7-4bit --prompt "Hello"
Details
- Base model
- sometimesanotion/Lamarck-14B-v0.7 (quantized)
- Vendor
- sometimesanotion
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 161 in the last 30 days · 2.0K all time · 1 likes
- Published
- 2025-02-19 · updated 2025-02-19 (1y ago)
- Languages
- en
- Tags
- qwen2, mergekit, merge, mlx-my-repo
Other MLX builds of sometimesanotion/Lamarck-14B-v0.7
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Lamarck-14B-v0.7-4bit (this one) | 4-bit | ≈ 8.3 GB | 16 GB+ | 161 |
| Lamarck-14B-v0.7-6bit | 6-bit | ≈ 12.0 GB | 16 GB+ | 26 |