GGUF
multilingual
gemma
quantized
llama.cpp
instruction-tuned
natural-language-processing
calibration
importance-matrix
resource-efficient
imatrix
conversational
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 agentlans/gemma-3-4b-it-GGUF:# Run inference directly in the terminal:
llama cli -hf agentlans/gemma-3-4b-it-GGUF:Use 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 agentlans/gemma-3-4b-it-GGUF:# Run inference directly in the terminal:
./llama-cli -hf agentlans/gemma-3-4b-it-GGUF:Build 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 agentlans/gemma-3-4b-it-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf agentlans/gemma-3-4b-it-GGUF:Use Docker
docker model run hf.co/agentlans/gemma-3-4b-it-GGUF:Quick Links
Gemma 3 4B Instruct Quantized Models
This repo offers quantized versions of google/gemma-3-4b-it for use with llama.cpp. Quantization was done using an unofficial Docker image and calibrated on 100 rows from the agentlans/LinguaNova dataset to maintain coherence and multilingual support. The importance matrix file is included.
Limitations
- Optimized for multilingual natural language tasks.
- May underperform on math, coding, and untested multimodal features.
- Shares all limitations and biases of the original Gemma 3 models.
Notes
- Ideal for resource-constrained environments.
- Test on your data for best results.
- See the original google/gemma-3-4b-it page for full details and guidelines.
This card covers only the quantized models.
- Downloads last month
- 36
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
8-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 agentlans/gemma-3-4b-it-GGUF:# Run inference directly in the terminal: llama cli -hf agentlans/gemma-3-4b-it-GGUF: