Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
eaddario
/
gemma-3-12b-it-pruned-GGUF
like
4
Text Generation
GGUF
eaddario/imatrix-calibration
English
quant
pruned
experimental
conversational
arxiv:
2406.17415
arxiv:
2403.03853
License:
gemma
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
69c26f6
gemma-3-12b-it-pruned-GGUF
121 GB
1 contributor
History:
10 commits
eaddario
Layer-wise & pruned quantization Q6_K
69c26f6
verified
6 months ago
imatrix
Generate imatrices
6 months ago
logits
Generate base model logits
6 months ago
.gitattributes
Safe
1.6 kB
Update .gitattributes
6 months ago
.gitignore
Safe
6.78 kB
Add .gitignore
6 months ago
README.md
Safe
26 Bytes
initial commit
6 months ago
gemma-3-12b-it-F16.gguf
Safe
23.5 GB
xet
Convert safetensor to GGUF @ F16
6 months ago
gemma-3-12b-it-pruned-Q6_K.gguf
9.01 GB
xet
Layer-wise & pruned quantization Q6_K
6 months ago
gemma-3-12b-it-pruned-Q8_0.gguf
11 GB
xet
Layer-wise & pruned quantization Q8_0
6 months ago
