# Can I run gpt-oss 20B on Apple M5 (32GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~13.2 GB of ~21 GB 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).
- Apple M5 (32GB): 32 GB unified, ~21 GB usable for model weights.
- Headroom: ~7.8 GB.

## How to run
Recommended quant: Q4_K_M. Best tool on macOS: LM Studio.

```sh
ollama run gpt-oss:20b
```

## 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 Apple M5 (32GB)
- [Qwen2.5 Coder 32B (32B)](https://localmodel.run/can-i-run/qwen2.5-coder-32b/apple-m5-32gb)
- [Granite 4.0 H Small (32B)](https://localmodel.run/can-i-run/granite-4.0-h-small/apple-m5-32gb)
- [Qwen3 30B-A3B (30.5B)](https://localmodel.run/can-i-run/qwen3-30b-a3b/apple-m5-32gb)
- [Gemma 2 27B (27B)](https://localmodel.run/can-i-run/gemma-2-27b/apple-m5-32gb)
- [Gemma 3 27B (27B)](https://localmodel.run/can-i-run/gemma-3-27b/apple-m5-32gb)
- [Mistral Small 3 24B (24B)](https://localmodel.run/can-i-run/mistral-small-3-24b/apple-m5-32gb)

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/apple-m5-32gb