text model · Qwen2.5-VL · Android
Can I run Qwen2.5-VL 3B on Google Pixel 9 Pro?
Yes. Qwen2.5-VL 3B runs on Google Pixel 9 Pro at Q4_K_M (~4.4 GB of ~10.5 GB usable).
Runs at Q4_K_M using ~4.4 GB of ~10.5 GB usable. You have room for FP16 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Google Pixel 9 Pro leaves ~6.1 GB of headroom, room to step up to FP16 for higher quality.
- Q4_K_M needed
- ~4.4 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
- Best quant
- Q4_K_M
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 3.75B
- Q4_K_M size
- 3.05 GB
- Q8_0 size
- 5.1 GB
- Context
- 32k
- Memory
- 16 GB ram
- Usable for weights
- ~10.5 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
You could also run
Run Qwen2.5-VL 3B on other hardware
FAQ
Can Google Pixel 9 Pro run Qwen2.5-VL 3B?
Yes. Qwen2.5-VL 3B runs on Google Pixel 9 Pro at Q4_K_M (~4.4 GB of ~10.5 GB usable).
How much memory does Qwen2.5-VL 3B need?
Google Pixel 9 Pro has room to spare. At Q4_K_M the weights are ~3.05 GB; with KV cache and runtime overhead, budget ~4.4 GB at a 4k context.
What is the best tool to run Qwen2.5-VL 3B on Android?
On Android, PocketPal AI (Polished app, download GGUF and run offline.) is the go-to option. NPU acceleration is limited and chip-specific; most apps run on CPU. Expect 1B-4B class.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/qwen2.5-vl-3b/pixel-9-pro) Sources
- 9to5google.com
- androidpolice.com
- comparigon.com
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- gsmarena.com/google_pixel_9_pro-12424.php
- gsmarena.com/google_pixel_9_pro-13218.php
- huggingface.co/ggml-org
- huggingface.co/Qwen
- layla-network.ai
- mlc.ai
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.