FuseChat-Llama-3.2-3B-Instruct-4bit
mlx-community/FuseChat-Llama-3.2-3B-Instruct-4bit
Uncategorised · 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.
Details
- Base model
- FuseAI/FuseChat-Llama-3.2-3B-Instruct (quantized)
- Vendor
- FuseAI
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 39 in the last 30 days · 4.7K all time · 1 likes
- Published
- 2025-01-29 · updated 2025-01-29 (1y ago)
- Tags
- llama