How to choose a model

Start with your phone’s RAM, because the model has to fit in memory alongside Android and your other apps. Pick the tier that matches, then use its default model. It’s the option OfflineMate suggests for that tier.

A larger model generally gives better answers, but it takes more storage and memory. If a model fails to load, the app can fall back to a lighter tier.

Want to ask about photos? Pick a vision model: LFM 2.5 VL 450M on Lite, LFM 2.5 VL 1.6B on Standard or Full, or Gemma 4 E2B multimodal on Full. They have an image icon in the app’s model list. The Gemma 4 E2B default on Standard reads text only; its multimodal build is a separate, larger download because it includes the vision and audio encoders.

Lite tier: 3–4 GB of RAM

For budget phones. Lite skips semantic notes search to stay fast.

ModelSizeRole
SmolLM2 135M~534 MBDefault
SmolLM2 360M~1.3 GBAlternative
LFM 2.5 350M~432 MBAlternative
LFM 2.5 VL 450M~619 MBAlternative

Standard tier: 6–8 GB of RAM

For most recent phones. Includes semantic search over your notes.

ModelSizeRole
Gemma 4 E2B~2.5 GBDefault
Llama 3.2 1B~1.1 GBAlternative
LFM 2.5 VL 1.6B~2.3 GBAlternative
Qwen 3 1.7B~1.2 GBAlternative
SmolLM2 1.7B~970 MBAlternative
Qwen 3.5 2B~2.9 GBAlternative
MiniCPM5 2B~1.3 GBAlternative

Full tier: 10–12+ GB of RAM

For flagship phones. Uses the largest models OfflineMate offers.

ModelSizeRole
Qwen 3 4B~2.6 GBDefault
Llama 3.2 3B~2.4 GBAlternative
LFM 2.5 VL 1.6B~2.3 GBAlternative
Gemma 4 E2B multimodal~4.2 GBAlternative
LFM 2.5 2.6B~1.7 GBAlternative

What the sizes mean

The sizes above are estimates for the chat model file alone. Setup also downloads speech and search files, so the total is higher: about 430 MB–1.3 GB for Lite, and about 2.5 GB for Standard and 2.6 GB for Full with their default models.

The “135M” or “4B” in a model’s name is its parameter count, in millions or billions. These builds are quantized, which shrinks them enough to run on a phone.

That’s why some Standard models, like Llama 3.2 1B or SmolLM2 1.7B, download at about 1 GB, less than some Lite files. The parameter count, not the download size, sets how much work the phone does for each word. A 1–2B model is many times more work than a Lite model. On a 3–4 GB phone it would answer very slowly or be closed by the system, so these models are in Standard, for phones with 6 GB of RAM or more.

OfflineMate downloads these models from Hugging Face. Select a model name in the tables above to see its source page.

New to local AI? Read how to run AI offline on Android.