gemma-3-27b-it-UQFF / README.md
EricB's picture
EricB HF Staff
Upload model
997a5fa verified
metadata
tags:
  - uqff
  - mistral.rs
base_model: google/gemma-3-27b-it
base_model_relation: quantized

google/gemma-3-27b-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.

Examples

Quantization type(s) Example
AFQ2 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f gemma3-27b-it-afq2-0.uqff
AFQ3 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq3-0.uqff;gemma3-27b-it-afq3-1.uqff"
AFQ4 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq4-0.uqff;gemma3-27b-it-afq4-1.uqff"
AFQ6 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq6-0.uqff;gemma3-27b-it-afq6-1.uqff;gemma3-27b-it-afq6-2.uqff"
AFQ8 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq8-0.uqff;gemma3-27b-it-afq8-1.uqff;gemma3-27b-it-afq8-2.uqff"
F8E4M3 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-f8e4m3-0.uqff;gemma3-27b-it-f8e4m3-1.uqff;gemma3-27b-it-f8e4m3-2.uqff"
Q2K ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f gemma3-27b-it-q2k-0.uqff
Q3K ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q3k-0.uqff;gemma3-27b-it-q3k-1.uqff"
Q4K ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q4k-0.uqff;gemma3-27b-it-q4k-1.uqff"
Q5K ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q5k-0.uqff;gemma3-27b-it-q5k-1.uqff"
Q8_0 ./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q8_0-0.uqff;gemma3-27b-it-q8_0-1.uqff;gemma3-27b-it-q8_0-2.uqff"