EXL3 Quants of google/gemma-3-270m-it
EXL3 quants of google/gemma-3-270m-it using exllamav3 for quantization.
Quants
Quant(Revision) | Bits per Weight | Head Bits |
---|---|---|
1.0_H8 | 1.0 | 8 |
1.5_H8 | 1.5 | 8 |
2.0_H8 | 2.0 | 8 |
2.5_H8 | 2.5 | 8 |
3.0_H8 | 3.0 | 8 |
3.5_H8 | 3.5 | 8 |
4.0_H8 | 4.0 | 8 |
4.5_H8 | 4.5 | 8 |
5.0_H8 | 5.0 | 8 |
5.5_H8 | 5.5 | 8 |
6.0_H8 | 6.0 | 8 |
6.5_H8 | 6.5 | 8 |
7.0_H8 | 7.0 | 8 |
7.5_H8 | 7.5 | 8 |
8.0_H8 | 8.0 | 8 |
Downloading quants with huggingface-cli
Click to view download instructions
Install hugginface-cli:
pip install -U "huggingface_hub[cli]"
Download quant by targeting the specific quant revision (branch):
huggingface-cli download ArtusDev/google_gemma-3-270m-it-EXL3 --revision "5.0bpw_H6" --local-dir ./
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support