calme-3.2-instruct-78b-4bit
mlx-community/calme-3.2-instruct-78b-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
78B
Weights (est.)
≈ 43.9 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/calme-3.2-instruct-78b-4bit --prompt "Hello"
Details
- Base model
- MaziyarPanahi/calme-3.2-instruct-78b (quantized)
- Vendor
- MaziyarPanahi
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- qwen
- Downloads
- 110 in the last 30 days · 736 all time · 1 likes
- Published
- 2024-12-15 · updated 2024-12-15 (1y ago)
- Languages
- en
- Tags
- qwen2, chat, qwen, qwen2.5, finetune, english, model-index