text model · Kimi · Android
Can I run Kimi K3 on Google Pixel 9 Pro?
No. Kimi K3 needs ~1522.2 GB even at Q4_K_M, but Google Pixel 9 Pro only has ~10.5 GB usable.
Needs ~1522.2 GB even at Q4_K_M, but only ~10.5 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 1511.7 GB: Kimi K3 needs roughly 1522.2 GB at Q4_K_M and Google Pixel 9 Pro leaves only about 10.5 GB usable for a model. No single tracked device has enough memory; Kimi K3 needs a multi-GPU or high-memory rig.
- Q4_K_M needed
- ~1522.2 GB
- Usable on device
- ~10.5 GB
- Device memory
- 16 GB
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 2800B (MoE, 104B active)
- Q4_K_M size
- 1508.67 GB
- Context
- 1000k
- Memory
- 16 GB ram
- Usable for weights
- ~10.5 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM (Adreno GPU path)
What you can run instead
FAQ
Can Google Pixel 9 Pro run Kimi K3?
No. Kimi K3 needs ~1522.2 GB even at Q4_K_M, but Google Pixel 9 Pro only has ~10.5 GB usable.
How much memory does Kimi K3 need?
Google Pixel 9 Pro does not have enough memory. At Q4_K_M the weights are ~1508.67 GB; with KV cache and runtime overhead, budget ~1522.2 GB at a 4k context. It is a Mixture-of-Experts model (2800B total / 104B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Kimi K3 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/kimi-k3/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/moonshotai
- huggingface.co/unsloth
- 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.