Can Gemma 4 E2B run on iPhone Air?

YESRuns great
Grade S · 90/100 · formula estimate

What this means

Our estimate says Gemma 4 E2B should fit comfortably on your iPhone Air.

Download the Q4_K_M version, which is about 3.1 GB. We expect it to use about 4 GB of the roughly 7.8 GB available to a model on this phone.

At the estimated speed, a roughly 300-word answer may take about 36 seconds to finish.

This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.

11.1tokens/s
estimated · faster than you read
4GB
needed at Q4_K_M
Q4_K_M
quant checked
S
grade · 90/100
needs 4 GBusable 7.8 GB
Apple A19 Pro12 GB RAMMetal

See how fast it feels

Estimated at 11.1 tokens/s — faster than you read. A ~300-word reply takes about 36 seconds on this phone.

Live demo · 11.1 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (3.1 GB) + mmap overhead3.3
KV cache4K context window0.1
Runtimellama.cpp + app overhead0.6
Total neededat Q4_K_M, 4K context4
Usable on iPhone Air12 GB RAM − iOS reserve (jetsam limit)7.8
Headroomleft for the OS and your other apps3.8

Pick your quant

QuantDownloadVerdictSpeed
Q3_K_M 2.5 GB Runs great~13.8 tokens/s
IQ4_XS 3 GB Runs great~11.5 tokens/s
Q4_0 3 GB Runs great~11.5 tokens/s
Q4_K_S 3 GB Runs great~11.5 tokens/s
Q4_K_M BEST HERE3.1 GB Runs great~11.1 tokens/s
Q5_K_M 3.4 GB Runs great~10.2 tokens/s
Q6_K 4.5 GB! Runs, barely~7.7 tokens/s
Q8_0 5 GB! Runs, barely~6.9 tokens/s

Get it running in 3 steps

1
Install PocketPal from the App Store — free, no account needed.
2
Download "Gemma 4 E2B Q4_K_M" in the in-app model hub — 3.1 GB, use Wi-Fi. Search Hugging Face for unsloth/gemma-4-E2B-it-GGUF and pick the Q4_K_M file.
3
Set context to 4K and enable Metal — expect ~11.1 tokens/s on this phone.

Related checks

MORE ON IPHONE AIR
Qwen3 0.6BQwen3 1.7BLlama 3.2 1BLlama 3.2 3BGemma 3 1B
GEMMA 4 E2B ON OTHER PHONES
OPPO Find X8 Provivo X200 ProGalaxy S26Galaxy S26+Galaxy S26 Ultra