Skip to content

zed-industries-zeta-fp16

mlx-community/zed-industries-zeta-fp16
Uncategorised · mlx
fp16 Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 15.2 GB
Mac memory (est.)
24 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
zed-industries/zeta (finetune)
Vendor
zed-industries
Task
Uncategorised
Quantisation
fp16
Licence
apache-2.0
Downloads
35 in the last 30 days · 420 all time · 0 likes
Published
2025-02-16 · updated 2025-02-16 (1y ago)
Tags
qwen2

Other MLX builds of zed-industries/zeta

Build Quantisation Weights Mac memory Downloads
zed-industries-zeta-4bit 4-bit ≈ 4.3 GB 8 GB+ 71
zed-industries-zeta-6bit 6-bit ≈ 6.2 GB 16 GB+ 73
zed-industries-zeta-8bit 8-bit ≈ 8.1 GB 16 GB+ 105
zed-industries-zeta-fp16 (this one) fp16 ≈ 15.2 GB 24 GB+ 35