Gemma · 12B · Desktop / import

Gemma 4 12B Instruct on a phone

2026 Gemma 4 12B — text, image, and audio. Mac or GPU; too big for phones.

Parameters
12B
Typical Q4
~7–8 GB (Q4/QAT)
RAM to budget
~11.5 GB
Engines
GGUF

Get it running

google/gemma-4-12B-it. Official QAT GGUF. 256K context. Host in LM Studio then chat from LM Mini. Hugging Face: google/gemma-4-12B-it.

Load in LM Studio or Ollama, then chat from the phone.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

  • None in this guide — use a Mac or Connect.

Tight (close other apps)

  • None in this guide — use a Mac or Connect.