CoolFace
Modelpublic

mistralrs-community/gemma-4-E4B-it-UQFF

sourceHugging Faceupdated 2mo agoView on Hugging Face
3likes180downloads
Model Card

google/gemma-4-E4B-it, UQFF quantization

Generated with mistral.rs 0.9.0. Documentation: UQFF docs.

1) Flexible ๐ŸŒ€: Multiple quantization formats in one file format with one framework to run them all. 2) Reliable ๐Ÿ”’: Compatibility ensured with embedded and checked semantic versioning information from day 1. 3) Easy ๐Ÿค—: Download UQFF models easily and quickly from Hugging Face, or use a local file. 4) Customizable ๐Ÿ› ๏ธ: Make and publish your own UQFF files in minutes.

Install

Install mistral.rs (full guide):

Linux/macOS:

curl --proto '=https' --tlsv1.2 -sSf https://raw.githubusercontent.com/EricLBuehler/mistral.rs/master/install.sh | sh

Windows (PowerShell):

irm https://raw.githubusercontent.com/EricLBuehler/mistral.rs/master/install.ps1 | iex

Examples

Note: AFQ variants are optimized for Apple Silicon / Metal.

QuantizationCommand
AFQ2mistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff afq2-0.uqff
AFQ3mistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff afq3-0.uqff
AFQ4mistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff afq4-0.uqff
AFQ6mistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff afq6-0.uqff
AFQ8mistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff afq8-0.uqff
Q2Kmistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff q2k-0.uqff
Q3Kmistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff q3k-0.uqff
Q4Kmistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff q4k-0.uqff
Q6Kmistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff q6k-0.uqff
Q8_0mistralrs run -m mistralrs-community/gemma-4-E4B-it-UQFF --from-uqff q8_0-0.uqff