text model · MiniMax · Android
Can I run MiniMax M3 on Google Pixel 9 Pro?
No. MiniMax M3 needs ~269.8 GB even at Q4_K_M, but Google Pixel 9 Pro only has ~10.5 GB usable.
Needs ~269.8 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 259.3 GB: MiniMax M3 needs roughly 269.8 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; MiniMax M3 needs a multi-GPU or high-memory rig.
- Q4_K_M needed
- ~269.8 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
- 428B (MoE, 23B active)
- Q4_K_M size
- 264.03 GB
- Q8_0 size
- 452.71 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 MiniMax M3?
No. MiniMax M3 needs ~269.8 GB even at Q4_K_M, but Google Pixel 9 Pro only has ~10.5 GB usable.
How much memory does MiniMax M3 need?
Google Pixel 9 Pro does not have enough memory. At Q4_K_M the weights are ~264.03 GB; with KV cache and runtime overhead, budget ~269.8 GB at a 4k context. It is a Mixture-of-Experts model (428B total / 23B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run MiniMax M3 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/minimax-m3/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/MiniMaxAI
- 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.