Gemma 2 9B (GGUF Q4)

Published by @quant_lab · Community adapter

Q4_K_M quantised Gemma 2 9B for offline deployment. Excellent summarisation and instruction following in 6 GB VRAM.

Usage

Load with Ollama:

# Download the adapter file, then create a Modelfile:
FROM gemma-2-9b-it
ADAPTER ./gemma2-9b-gguf-q4.gguf

# Build and run:
ollama create my-model -f Modelfile
ollama run my-model "Your prompt here"

Or with llama.cpp:

./llama-cli \
  -m base-model.gguf \
  --lora gemma2-9b-gguf-q4.gguf \
  -p "Your prompt here"

Compatibility

• llama.cpp
• Ollama
• LM Studio