Google
Gemma 4 QAT E4B
Google’s compact assistant for writing and everyday questions. E means effective parameters; the full download is larger. Text chat only.
About Gemma 4 QAT E4B
Gemma 4 QAT E4B is the larger of Google's quantization-aware on-device models, with noticeably stronger writing and reasoning than E2B. The QAT Q4_0 build is about a 5.2 GB download and needs a phone with 10 GB or more of memory.
Every model in this catalog runs locally in the Offline AI Chat app. After the download finishes, Gemma 4 QAT answers on your phone with no connection, and your prompts and replies are never uploaded.
- Download size
- 5.2 GB (Q4_0 GGUF)
- Memory needed
- 10 GB minimum · 12 GB recommended
- Context in app
- 2,048 tokens
- Runs on
- Android 8+, 64-bit · iOS in private testing
- Access
- Offline Plus subscription
- License
- Apache-2.0
- Model source
- Google on Hugging Face