This is a requantized version of https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-gguf based off of stduhpf's changes, but with some small fixes. Several tokens were set to control instead of normal, and name metadata was added.
See the discussion at https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-gguf/discussions/3#67f6a2e0207b4bceea793151 for more information. This is similar to https://huggingface.co/Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix/ but for the 27b model.
- Downloads last month
- 231
Hardware compatibility
Log In
to view the estimation
4-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.
Model tree for jaxchang/google-gemma-3-27b-it-qat-q4_0-gguf-fix
Base model
google/gemma-3-27b-pt
Finetuned
google/gemma-3-27b-it
Quantized
google/gemma-3-27b-it-qat-q4_0-gguf