Skip to content

Apriel-1.5-15b-Thinker-5bit

mlx-community/Apriel-1.5-15b-Thinker-5bit
Text generation · transformers
5-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/Apriel-1.5-15b-Thinker-5bit --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
5-bit
Licence
mit
Downloads
36 in the last 30 days · 436 all time · 0 likes
Published
2025-10-01 · updated 2025-10-03 (1y ago)
Tags
pixtral, image-text-to-text