Can Llama 3.2 1B run on Moto G Stylus (2025)?

YESRuns great
Grade S · 98/100 · formula estimate

What this means

Our estimate says Llama 3.2 1B should fit comfortably on your Moto G Stylus (2025).

Download the Q4_K_M version, which is about 0.8 GB. We expect it to use about 1.5 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 28 seconds to finish.

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

14.4tokens/s
estimated · faster than you read
1.5GB
needed at Q4_K_M
Q4_K_M
quant checked
S
grade · 98/100
needs 1.5 GBusable 6 GB
Snapdragon 6 Gen 38 GB RAMCPU / GPU

See how fast it feels

Estimated at 14.4 tokens/s — faster than you read. A ~300-word reply takes about 28 seconds on this phone.

Live demo · 14.4 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (0.8 GB) + mmap overhead0.8
KV cache4K context window0.1
Runtimellama.cpp + app overhead0.6
Total neededat Q4_K_M, 4K context1.5
Usable on Moto G Stylus (2025)8 GB RAM − Android system reserve6
Headroomleft for the OS and your other apps4.5

Pick your quant

QuantDownloadVerdictSpeed
IQ4_XS 0.7 GB Runs great~16.5 tokens/s
Q4_0 0.8 GB Runs great~14.4 tokens/s
Q4_K_M BEST HERE0.8 GB Runs great~14.4 tokens/s
Q4_K_S 0.8 GB Runs great~14.4 tokens/s
Q5_K_M 0.9 GB Runs great~12.8 tokens/s
Q6_K 1 GB Runs great~11.5 tokens/s
Q8_0 1.3 GB Runs great~8.9 tokens/s

Get it running in 3 steps

1
Install PocketPal from the Play Store — free, no account needed.
2
Download "Llama 3.2 1B Q4_K_M" in the in-app model hub — 0.8 GB, use Wi-Fi. Search Hugging Face for bartowski/Llama-3.2-1B-Instruct-GGUF and pick the Q4_K_M file.
3
Set context to 4K — expect ~14.4 tokens/s on this phone.

Related checks

MORE ON MOTO G STYLUS (2025)
Qwen3 0.6BTernary Bonsai 1.7BGemma 3 1BDeepSeek R1 Distill 1.5BSmolLM2 1.7B
LLAMA 3.2 1B ON OTHER PHONES
Galaxy S25 UltraGalaxy S25Galaxy S24 UltraGalaxy S24Galaxy S23 Ultra