deepcogito-cogito-v1-preview-llama-3B-4bit
mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
3.2B
Weights (est.)
≈ 1.8 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit --prompt "Hello"
Details
- Base model
- deepcogito/cogito-v1-preview-llama-3B (quantized)
- Vendor
- deepcogito
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3.2
- Downloads
- 179 in the last 30 days · 12K all time · 0 likes
- Published
- 2025-04-08 · updated 2025-04-08 (1y ago)
- Tags
- llama
Other MLX builds of deepcogito/cogito-v1-preview-llama-3B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| deepcogito-cogito-v1-preview-llama-3B-4bit (this one) | 4-bit | ≈ 1.8 GB | 8 GB+ | 179 |
| deepcogito-cogito-v1-preview-llama-3B-6bit | 6-bit | ≈ 2.6 GB | 8 GB+ | 26 |
| deepcogito-cogito-v1-preview-llama-3B-8bit | 8-bit | ≈ 3.4 GB | 8 GB+ | 29 |
| deepcogito-cogito-v1-preview-llama-3B-fp16 | fp16 | ≈ 6.4 GB | 16 GB+ | 23 |
| deepcogito-cogito-v1-preview-llama-3B-bf16 | bf16 | ≈ 6.4 GB | 16 GB+ | 18 |