How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_S# Run inference directly in the terminal:
llama cli -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_SUse pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_S# Run inference directly in the terminal:
./llama-cli -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_SBuild from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_S# Run inference directly in the terminal:
./build/bin/llama-cli -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_SUse Docker
docker model run hf.co/Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_SQuick Links
https://huggingface.co/stduhpf/google-gemma-3-12b-it-qat-q4_0-gguf-small but with tokens 105 and 106 and their corresponding image tokens set to control instead of normal. Added general.name metadata.
- Downloads last month
- 13,024
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_S# Run inference directly in the terminal: llama cli -hf Dampfinchen/google-gemma-3-12b-it-qat-q4_0-gguf-small-fix:Q4_0_S