Unsloth Gemma-4 QAT GGUF
Quantized GGUF versions of Google's Gemma 4 12B instruct model optimized for speed.
huggingface.coBuilt with
UnknownBuild evidence
Strong
The page is a direct, verified repository on Hugging Face containing the functional GGUF model files released by the Unsloth AI team.
Creator
Unsloth AI @unslothShipped
1h agoThese quantized GGUF weights allow developers to run Google's Gemma 4 12B model locally using tools like llama.cpp or Unsloth Studio. By providing QAT (Quantization Aware Training) GGUF formats, these files enable efficient high-performance inference on consumer hardware.
Timeline
Teaser
Video
Playable
Product
Loading…
