Skip to content
localmodel.run

text model · gpt-oss · Android

Can I run gpt-oss 120B on Generic Android Phone (8GB RAM)?

Compatibility verdict VRAM threshold engine
No, not enough memorywould not load

No. gpt-oss 120B needs ~62.4 GB even at Q4_K_M, but Generic Android Phone (8GB RAM) only has ~4.5 GB usable.

Needs ~62.4 GB Device usable ~4.5 GB

Needs ~62.4 GB even at Q4_K_M, but only ~4.5 GB is usable.

Q4_K_M needed
~62.4 GB
Usable on device
~4.5 GB
Device memory
8 GB

How to run it

On Android use PocketPal AI (Polished app, download GGUF and run offline.). NPU acceleration is limited and chip-specific; most apps run on CPU. Expect 1B-4B class.

Model gpt-oss
Parameters
117B (MoE, 5.1B active)
Q4_K_M size
59.03 GB
Context
128k
Ollama tag
gpt-oss:120b
Full gpt-oss 120B requirements →
Device Android
Memory
8 GB ram
Usable for weights
~4.5 GB
Best runtime
llama.cpp (PocketPal or SmolChat)
Best models for Generic Android Phone (8GB RAM) →

What you can run instead

Run gpt-oss 120B on other hardware

FAQ

Can Generic Android Phone (8GB RAM) run gpt-oss 120B?

No. gpt-oss 120B needs ~62.4 GB even at Q4_K_M, but Generic Android Phone (8GB RAM) only has ~4.5 GB usable.

How much memory does gpt-oss 120B need?

Generic Android Phone (8GB RAM) does not have enough memory. At Q4_K_M the weights are ~59.03 GB; with KV cache and runtime overhead, budget ~62.4 GB at a 4k context. It is a Mixture-of-Experts model (117B total / 5.1B active), so all experts must stay in memory; memory tracks total params, not active params.

What is the best tool to run gpt-oss 120B 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.

Sources

Memory figures are estimates. See methodology.