Skip to content

d1a-e4b-8bit

mlx-community/d1a-e4b-8bit
8-bit Open on Hugging Face
Parameters
7.5B
Weights (est.)
≈ 7.9 GB
Mac memory (est.)
16 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
JohnP1/d1a-e4b (quantized)
Vendor
JohnP1
Task
Text classification
Quantisation
8-bit
Licence
apache-2.0
Downloads
93 in the last 30 days · 105 all time · 0 likes
Published
2026-10-11 · updated 2026-10-25 (17d ago)
Languages
en, ja
Tags
gemma4, d1a, decision-model, structured-output, classification, apple-silicon, quantized, pull-requests