Will this model run on your hardware?

Can I run Google: Gemma 3 4B locally?

• 4.3B parameters
• licence: gemma
• Weights: google/gemma-3-4b-it · GGUF: unsloth/gemma-3-4b-it-GGUF

Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.

Quantizations and file sizes

Run it locally

ollama run hf.co/unsloth/gemma-3-4b-it-GGUF:Q4_K_M

llama serve -hf unsloth/gemma-3-4b-it-GGUF:Q4_K_M

LM Studio: open unsloth/gemma-3-4b-it-GGUF