LookAtMyQuant
github.com/shinmegamiboson/lookatmyquant- Category
- AI Tools
- Rank
- No. 1212Tools index
- Pricing
- Open Source
- Type
- TOOL
- GitHub
- 199 stars
- Latest release
- lm2-qwen35-4b-1.2gb
- Date
About
LookAtMyQuant is a quantization compiler that measures how much compressing each part of a model hurts output, then picks a code for each part so the model fits a size budget with the least damage. The README reports compressed builds of Gemma 4 E2B, Qwen3.5-4B, Qwen3.8-27B and Inkling-2-Mini, including Inkling-2-Mini at 5.4 GB and 8.9 GB, with benchmark comparisons against Unsloth GGUFs. Results are the author's own reports.
Tags
quantizationllmcompressionmlxggufapple-silicon
Tech Stack
Python
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.