Skip to content

Magicoder-S-DS-6.7B-4bit-mlx

mlx-community/Magicoder-S-DS-6.7B-4bit-mlx
Text generation · transformers
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—

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/Magicoder-S-DS-6.7B-4bit-mlx --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
4-bit
Licence
deepseek
Downloads
42 in the last 30 days · 469 all time · 0 likes
Published
2024-01-09 · updated 2024-01-14 (2y ago)
Tags
llama