Gemma · 4.5B · Desktop / import
Gemma 4 E4B Instruct on a phone
Google’s on-device Gemma 4 (~4.5B effective) with image and audio. The 2026 upgrade from Gemma 3 4B / 3n E4B.
- Parameters
- 4.5B
- Typical Q4
- ~2.6–3.2 GB (Q4/QAT)
- RAM to budget
- ~4.4 GB
- Engines
- GGUF
Get it running
google/gemma-4-E4B-it. Official QAT GGUF. ~8B with embeddings; budget ~4 GB live. Apache 2.0. Hugging Face: google/gemma-4-E4B-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
- iPhone 17 Pro Max Runs well
- iPhone 17 Pro Runs well
- iPhone Air Runs well
- Pixel 10 Pro XL Runs well
- Pixel 10 Pro Runs well
- Pixel 10 Runs well
- Galaxy S26 Ultra Runs well
- Pixel 9 Pro XL Runs well
- Pixel 9 Pro Runs well
- Pixel 9 Runs well
- Pixel 8 Pro Runs well
- Galaxy S25 Ultra Runs well
- Galaxy S25 Runs well
- Galaxy S24 Ultra Runs well
- Galaxy S23 Ultra Runs well
- OnePlus 13 Runs well
- OnePlus 12 Runs well
- Xiaomi 15 Runs well
Tight (close other apps)
- Pixel 9a Tight
- Pixel 8 Tight
- Galaxy S24 Tight
- Galaxy S23 Tight
- Nothing Phone (2a) Tight
- Redmi Note 14 Pro Tight
- iPad Pro (M4) Tight
- iPad Air (M3) Tight
- Pixel Tablet Tight