text model · gpt-oss · macOS
Can I run gpt-oss 20B on Apple M4 Pro (48GB)?
Yes. gpt-oss 20B runs on Apple M4 Pro (48GB) at Q4_K_M (~13.2 GB of ~32 GB usable).
Runs at Q4_K_M using ~13.2 GB of ~32 GB usable. You have room for Q8_0 for higher quality.
That figure is at a 4k context and moves about ±15% as context length changes. Apple M4 Pro (48GB) leaves ~18.8 GB of headroom, room to step up to Q8_0 for higher quality.
- Q4_K_M needed
- ~13.2 GB
- Usable on device
- ~32 GB
- Device memory
- 48 GB
- Best quant
- Q4_K_M
Which quant fits
Run it
Pick your tool. All 3 load the same Q4_K_M weights.
ollama run gpt-oss:20b llama-cli -hf ggml-org/gpt-oss-20b-GGUF:Q4_K_M lms get ggml-org/gpt-oss-20b-GGUF - Parameters
- 21B (MoE, 3.6B active)
- Q4_K_M size
- 11.28 GB
- Q8_0 size
- 0.86 GB
- Context
- 128k
- Ollama tag
- gpt-oss:20b
- Memory
- 48 GB unified
- Usable for weights
- ~32 GB
- Power draw
- ~140 W
- Best runtime
- Ollama (MLX backend) / MLX direct
You could also run
Run gpt-oss 20B on other hardware
FAQ
Can Apple M4 Pro (48GB) run gpt-oss 20B?
Yes. gpt-oss 20B runs on Apple M4 Pro (48GB) at Q4_K_M (~13.2 GB of ~32 GB usable).
How much memory does gpt-oss 20B need?
Apple M4 Pro (48GB) has room to spare. At Q4_K_M the weights are ~11.28 GB; with KV cache and runtime overhead, budget ~13.2 GB at a 4k context. It is a Mixture-of-Experts model (21B total / 3.6B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run gpt-oss 20B on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/gpt-oss-20b/apple-m4-pro-48gb) Sources
- apple.com/newsroom/2024/10/apple-introduces-m4-pro-and-m4-max
- apple.com/newsroom/2024/10/new-macbook-pro-features-m4-family-of-chips-and-apple-intelligence
- blog.peddals.com
- github.com/ml-explore
- github.com/raullenchai
- huggingface.co/ggml-org
- huggingface.co/openai
- lmstudio.ai
- ollama.com/library/gpt-oss
- ollama.com/library/gpt-oss/tags
- support.apple.com/en-us/103253
- support.apple.com/en-us/121553
- support.apple.com/en-us/121555
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.