Can Gemma 3 12B run on Galaxy S25 FE?

YESRuns great
Grade A · 79/100 · formula estimate

What this means

Our estimate says Gemma 3 12B should fit comfortably on your Galaxy S25 FE.

Download the IQ1_S version, which is about 3.1 GB. We expect it to use about 4.7 GB of the roughly 6 GB available to a model on this phone.

At the estimated speed, a roughly 300-word answer may take about 41 seconds to finish.

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

9.8tokens/s
estimated · faster than you read
4.7GB
needed at IQ1_S
IQ1_S
quant checked
A
grade · 79/100
needs 4.7 GBusable 6 GB
Samsung Exynos 24008 GB RAMCPU / GPU

See how fast it feels

Estimated at 9.8 tokens/s — faster than you read. A ~300-word reply takes about 41 seconds on this phone.

Live demo · 9.8 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsIQ1_S GGUF (3.1 GB) + mmap overhead3.3
KV cache4K context window0.9
Runtimellama.cpp + app overhead0.6
Total neededat IQ1_S, 4K context4.7
Usable on Galaxy S25 FE8 GB RAM − Android system reserve6
Headroomleft for the OS and your other apps1.3

Pick your quant

QuantDownloadVerdictSpeed
IQ1_S BEST HERE3.1 GB Runs great~9.8 tokens/s
Q2_K 4.8 GB Won't fitwon't fit
Q3_K_M 6 GB Won't fitwon't fit
IQ4_XS 6.6 GB Won't fitwon't fit
Q4_0 6.9 GB Won't fitwon't fit
Q4_K_S 6.9 GB Won't fitwon't fit
Q4_K_M 7.3 GB Won't fitwon't fit
Q5_K_M 8.4 GB Won't fitwon't fit
Q6_K 9.7 GB Won't fitwon't fit
Q8_0 12.5 GB Won't fitwon't fit

Get it running in 3 steps

1
Install PocketPal from the Play Store — free, no account needed.
2
Download "Gemma 3 12B IQ1_S" in the in-app model hub — 3.1 GB, use Wi-Fi. Search Hugging Face for unsloth/gemma-3-12b-it-GGUF and pick the IQ1_S file.
3
Set context to 4K — expect ~9.8 tokens/s on this phone.

Related checks

MORE ON GALAXY S25 FE
Qwen3 0.6BQwen3 1.7BLlama 3.2 1BLlama 3.2 3BGemma 3 1B
GEMMA 3 12B ON OTHER PHONES
OPPO Find X8 Provivo X200 ProGalaxy S26 UltraXiaomi 17Xiaomi 17 Pro