Can SmolLM3 3B run on Pixel 9a?

YESRuns great
Grade S · 100/100 · formula estimate

What this means

Our estimate says SmolLM3 3B should fit comfortably on your Pixel 9a.

Download the Q4_K_M version, which is about 1.9 GB. We expect it to use about 2.8 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 25 seconds to finish.

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

16.2tokens/s
estimated · instant
2.8GB
needed at Q4_K_M
Q4_K_M
quant checked
S
grade · 100/100
needs 2.8 GBusable 6 GB
Google Tensor G48 GB RAMCPU / GPU

See how fast it feels

Estimated at 16.2 tokens/s — instant. A ~300-word reply takes about 25 seconds on this phone.

Live demo · 16.2 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (1.9 GB) + mmap overhead2
KV cache4K context window0.2
Runtimellama.cpp + app overhead0.6
Total neededat Q4_K_M, 4K context2.8
Usable on Pixel 9a8 GB RAM − Android system reserve6
Headroomleft for the OS and your other apps3.2

Pick your quant

QuantDownloadVerdictSpeed
Q2_K 1.3 GB Runs great~23.6 tokens/s
Q3_K_M 1.6 GB Runs great~19.2 tokens/s
IQ4_XS 1.7 GB Runs great~18.1 tokens/s
Q4_0 1.8 GB Runs great~17.1 tokens/s
Q4_K_S 1.8 GB Runs great~17.1 tokens/s
Q4_K_M BEST HERE1.9 GB Runs great~16.2 tokens/s
Q5_K_M 2.2 GB Runs great~14 tokens/s
Q6_K 2.5 GB Runs great~12.3 tokens/s
Q8_0 3.3 GB Runs great~9.3 tokens/s

Get it running in 3 steps

1
Install PocketPal from the Play Store — free, no account needed.
2
Download "SmolLM3 3B Q4_K_M" in the in-app model hub — 1.9 GB, use Wi-Fi. Search Hugging Face for unsloth/SmolLM3-3B-GGUF and pick the Q4_K_M file.
3
Set context to 4K — expect ~16.2 tokens/s on this phone.

Related checks

MORE ON PIXEL 9A
Qwen3 0.6BQwen3 1.7BLlama 3.2 1BLlama 3.2 3BGemma 3 1B
SMOLLM3 3B ON OTHER PHONES
Galaxy S25 UltraGalaxy S25Galaxy S24 UltraGalaxy S24Galaxy S23 Ultra