This page contains quantized GGUF files for the model sam-paech/gemma-3-12b-it-dm-001.

Quants are made with imatrix calibration using Bartowski's public imatrix dataset.

The graph below gives a good idea on how these quants should perform. Data is grabbed from the llama.cpp page on perplexity. image/png

Downloads last month
2,284
GGUF
Model size
11.8B params
Architecture
gemma3
Hardware compatibility
Log In to view the estimation

3-bit

4-bit

5-bit

6-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Sketchfellow/sam-paech-gemma-3-12b-it-dm-001-GGUF

Quantized
(1)
this model