Can Qwen 3.6 35B-A3B run on OnePlus 12?

YESRuns great
Formula estimate

What this means

Our estimate says Qwen 3.6 35B-A3B should fit comfortably on your OnePlus 12.

Download the IQ4_XS version, which is about 17.7 GB. We expect it to use about 19.3 GB of the roughly 20 GB available to a model on this phone.

At the estimated speed, a roughly 300-word answer may take about 18 seconds to finish.

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

22.8tokens/s
estimated · instant
19.3GB
needed at IQ4_XS
IQ4_XS
quant checked
needs 19.3 GBusable 20 GB
Snapdragon 8 Gen 324 GB RAMCPU / GPUAlso sold with 12/16 GB

See how fast it feels

Estimated at 22.8 tokens/s — instant. A ~300-word reply takes about 18 seconds on this phone.

Live demo · 22.8 tokens/s

Where the memory goes

ComponentDetailGB
Model weightsIQ4_XS GGUF (17.7 GB) + mmap overhead18.6
KV cache4K context window0.1
Runtimellama.cpp + app overhead0.6
Total neededat IQ4_XS, 4K context19.3
Working budget24 GB RAM Android system reserve20
Headroomremaining inside the working budget0.7

Pick your quant

QuantDownloadVerdictSpeed
Q3_K_M 16.6 GB Runs great~24.3 tokens/s
IQ4_XS BEST HERE17.7 GB Runs great~22.8 tokens/s
Q4_K_S 20.9 GB Won't fitwon't fit
MXFP4 21.7 GB Won't fitwon't fit
Q4_K_M 22.1 GB Won't fitwon't fit
Q5_K_M 26.5 GB Won't fitwon't fit
Q6_K 29.3 GB Won't fitwon't fit
Q8_0 36.9 GB Won't fitwon't fit

Get your first offline chat working

Recommended app: PocketPal. Follow the point-and-click steps below. The speed above is an estimate, not a measurement from this exact app and phone.
1
Install or update PocketPal from Google Play. It is free and does not require an account. Use a current version so its loader supports newer model architectures.
2
Open the exact model. In PocketPal, go to Models → + → Add from Hugging Face, then paste unsloth/Qwen3.6-35B-A3B-GGUF.
3
Choose the IQ4_XS GGUF file. The download is about 17.7 GB, so use Wi-Fi and keep the app open. Choose the main GGUF weights, not a vision projector, mmproj, or other helper file.
4
Tap Download, then Load. Start with a 4K (4096-token) context. Keep the app’s default Android backend for the first run.
5
Send a simple first prompt. Try “Explain why the sky is blue in three sentences.” This page estimates about 22.8 tokens/s, but that number is not a PocketPal measurement unless it carries a ✓ Verified label.
6
Confirm it is really offline. After the first reply, turn on airplane mode and ask a second question. If it still answers, the model is running on your phone.
If it does not work
  • Model not listed: update PocketPal and paste the exact repository unsloth/Qwen3.6-35B-A3B-GGUF.
  • App closes while loading: close other apps, restart the phone, and try 2K context. If it still closes, choose a smaller model.
  • No offline reply: confirm that the IQ4_XS GGUF file is loaded in the chat rather than a remote model.

Related checks

More on OnePlus 12
Qwen3 0.6BQwen3 1.7BLlama 3.2 1BLlama 3.2 3BGemma 3 1B
Qwen 3.6 35B-A3B on other phones
OnePlus 13ROG Phone 9 ProHuawei Mate X7Galaxy S25 UltraGalaxy S25