language:
- en
license: other
base_model: TrevorJS/gemma-4-26B-A4B-it-uncensored
tags: - nvfp4
- gguf
- llama.cpp
- gemma
gemma-4-26B-A4B-it-uncensored-NVFP4-GGUF
This repository contains the NVFP4 GGUF weights for TrevorJS/gemma-4-26B-A4B-it-uncensored, converted using llama.cpp's native GGML_TYPE_NVFP4 layout.
Model Files
gemma-4-26B-A4B-it-uncensored-NVFP4.gguf: NVFP4 quantized model file.
Usage with llama.cpp
Run using a modern build of llama.cpp supporting NVFP4:
# Interactive CLI
llama-cli -m gemma-4-26B-A4B-it-uncensored-NVFP4.gguf -p "Hello, world!" -n 256
# Or start llama-server
llama-server -m gemma-4-26B-A4B-it-uncensored-NVFP4.gguf --port 8080 -ngl 99