Downloads · 30 days
64
20% of all-time downloads
gemma-4-12B-it-qat-Q4_0_V2
Pajari/gemma-4-12B-it-qat-Q4_0_V2
gemma-4-12B-it-qat-Q4_0_V2 is a machine learning model from Pajari. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
Quantization of Google's Gemma 4 12B QAT checkpoint using a modified Q40 encoder that better preserves QAT weight geometry under standard GGUF FP16 block scales.
All-time downloads
319
Public
Repo size
13.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf7 GB · 100%
At a glance
- License
- gemma
- Access
- Public
- Created
- Jun 16, 2026
- Updated
- Jun 25, 2026
- SHA
- 4dbf244d
Base models
Model card
From the Hugging Face model README
Gemma 4 12B QAT Q4_0_V2
Quantization of Google's Gemma 4 12B QAT checkpoint using a modified Q4_0 encoder that better preserves QAT weight geometry under standard GGUF FP16 block scales.
This GGUF utilizes the same encoding methodology that achieved a measured 7× reduction in KL divergence on the /Pajari/gemma-4-31B-it-qat-Q4_0_V2 model.
Q4_0_V2 will run in normal mainline llama.cpp.
- License
- gemma
- Created
- Jun 16, 2026
- Updated
- Jun 25, 2026