# Can I run gpt-oss 20B on iPhone 17 Pro?

> **No, not enough memory.** Needs ~13.2 GB even at Q4_K_M, but only ~8 GB is usable.

Last validated: 2026-06-15.

## Memory math
- gpt-oss 20B: 21B (MoE, 3.6B active); Q4_K_M weighs 11.28 GB on disk.
- At Q4_K_M with a 4k context it needs ~13.2 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- iPhone 17 Pro: 12 GB unified, ~8 GB usable for model weights.
- Headroom: ~-5.2 GB.

## How to run
Recommended quant: n/a. Best tool on iOS: Apple Foundation Models.

## Run gpt-oss 20B on other devices
- [Nvidia GeForce RTX 4060 Ti (16GB)](https://localmodel.run/can-i-run/gpt-oss-20b/nvidia-rtx-4060-ti-16gb)
- [Nvidia GeForce RTX 4080 (16GB)](https://localmodel.run/can-i-run/gpt-oss-20b/nvidia-rtx-4080-16gb)
- [Apple M4 (24GB)](https://localmodel.run/can-i-run/gpt-oss-20b/apple-m4-24gb)
- [Apple M4 Pro (24GB)](https://localmodel.run/can-i-run/gpt-oss-20b/apple-m4-pro-24gb)
- [Nvidia GeForce RTX 4090 (24GB)](https://localmodel.run/can-i-run/gpt-oss-20b/nvidia-rtx-4090-24gb)
- [Nvidia GeForce RTX 3090 (24GB)](https://localmodel.run/can-i-run/gpt-oss-20b/nvidia-rtx-3090-24gb)

## Other models that run on iPhone 17 Pro
- [Falcon3 10B (10B)](https://localmodel.run/can-i-run/falcon3-10b/iphone-17-pro)
- [Gemma 2 9B (9B)](https://localmodel.run/can-i-run/gemma-2-9b/iphone-17-pro)
- [GLM-4 9B (9B)](https://localmodel.run/can-i-run/glm-4-9b/iphone-17-pro)
- [Qwen2.5-VL 7B (8.29B)](https://localmodel.run/can-i-run/qwen2.5-vl-7b/iphone-17-pro)
- [Llama 3.1 8B (8B)](https://localmodel.run/can-i-run/llama-3.1-8b/iphone-17-pro)
- [Qwen3 8B (8B)](https://localmodel.run/can-i-run/qwen3-8b/iphone-17-pro)

Estimate, not a guarantee. Sources: https://ollama.com/library/gpt-oss, https://ollama.com/library/gpt-oss/tags, https://huggingface.co/ggml-org/gpt-oss-20b-GGUF, https://huggingface.co/openai/gpt-oss-20b.
More: https://localmodel.run/can-i-run/gpt-oss-20b/iphone-17-pro