# Can I run gpt-oss 20B on Apple M4 Pro (24GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~13.2 GB of ~16 GB usable.

- Model: 21B (MoE, 3.6B active), Q4_K_M 11.28 GB
- Device: 24 GB unified, ~16 GB usable for weights
- Needs ~13.2 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on macOS: LM Studio
- Command: `ollama run gpt-oss:20b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. 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-m4-pro-24gb