text model · OLMo · Android
Can I run OLMo 2 32B Instruct on Generic Android Phone (12GB RAM)?
No. OLMo 2 32B Instruct needs ~21.7 GB even at Q4_K_M, but Generic Android Phone (12GB RAM) only has ~8.5 GB usable.
Needs ~21.7 GB even at Q4_K_M, but only ~8.5 GB is usable.
That figure is at a 4k context and moves about ±15% as context length changes.
The gap is about 13.2 GB: OLMo 2 32B Instruct needs roughly 21.7 GB at Q4_K_M and Generic Android Phone (12GB RAM) leaves only about 8.5 GB usable for a model. The lightest tracked hardware that runs OLMo 2 32B Instruct is the Nvidia GeForce RTX 4090 (24GB) at 24 GB. See OLMo 2 32B Instruct on Nvidia GeForce RTX 4090 (24GB).
- Q4_K_M needed
- ~21.7 GB
- Usable on device
- ~8.5 GB
- Device memory
- 12 GB
Which quant fits
How to run it
On Android use PocketPal AI (Polished app, download GGUF and run offline.).
- Parameters
- 32B
- Q4_K_M size
- 19.5 GB
- Q8_0 size
- 34.3 GB
- Context
- 4k
- Memory
- 12 GB ram
- Usable for weights
- ~8.5 GB
- Best runtime
- llama.cpp (PocketPal) or MLC-LLM
What you can run instead
Run OLMo 2 32B Instruct on other hardware
FAQ
Can Generic Android Phone (12GB RAM) run OLMo 2 32B Instruct?
No. OLMo 2 32B Instruct needs ~21.7 GB even at Q4_K_M, but Generic Android Phone (12GB RAM) only has ~8.5 GB usable.
How much memory does OLMo 2 32B Instruct need?
Generic Android Phone (12GB RAM) does not have enough memory. At Q4_K_M the weights are ~19.5 GB; with KV cache and runtime overhead, budget ~21.7 GB at a 4k context.
What is the best tool to run OLMo 2 32B Instruct 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/olmo-2-32b/android-generic-12gb) Sources
- github.com/a-ghorbani
- github.com/google-ai-edge
- github.com/mlc-ai
- github.com/shubham0204
- github.com/Vali-98
- huggingface.co/allenai/OLMo-2-0325-32B
- huggingface.co/allenai/OLMo-2-0325-32B-Instruct
- huggingface.co/allenai/OLMo-2-0325-32B-Instruct-GGUF
- huggingface.co/bartowski
- huggingface.co/unsloth
- layla-network.ai
- ollama.com/library/llama3.1:8b
- ollama.com/library/olmo2
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.