google/gemma-4-31B-it, UQFF quantization

Run with mistral.rs. 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

Running

With an image:

mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff 8 --image image.png -i "Describe this image in detail."

With a video:

mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff 8 --video video.mp4 -i "Describe this video in detail."

Examples

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

Quantization Command
AFQ2 mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff afq2-0.uqff
AFQ3 mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff afq3-0.uqff
AFQ4 mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff afq4-0.uqff
AFQ6 mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff afq6-0.uqff
AFQ8 mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff afq8-0.uqff
Q2K mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff q2k-0.uqff
Q3K mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff q3k-0.uqff
Q4K mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff q4k-0.uqff
Q5K mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff q5k-0.uqff
Q6K mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff q6k-0.uqff
Q8_0 mistralrs run -m mistralrs-community/gemma-4-31B-it-UQFF --from-uqff q8_0-0.uqff
Downloads last month
82
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mistralrs-community/gemma-4-31B-it-UQFF

Quantized
(107)
this model