text model · gpt-oss · macOS
Can I run gpt-oss 120B on Apple M4 Max (128GB)?
Yes. gpt-oss 120B runs on Apple M4 Max (128GB) at Q4_K_M (~62.4 GB of ~96 GB usable).
Runs at Q4_K_M using ~62.4 GB of ~96 GB usable.
- Q4_K_M needed
- ~62.4 GB
- Usable on device
- ~96 GB
- Device memory
- 128 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run gpt-oss:120b llama-cli -hf ggml-org/gpt-oss-120b-GGUF:Q4_K_M lms get ggml-org/gpt-oss-120b-GGUF 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.
- Parameters
- 117B (MoE, 5.1B active)
- Q4_K_M size
- 59.03 GB
- Context
- 128k
- Ollama tag
- gpt-oss:120b
- Memory
- 128 GB unified
- Usable for weights
- ~96 GB
- Best runtime
- MLX direct / Ollama (MLX backend)
You could also run
Run gpt-oss 120B on other hardware
FAQ
Can Apple M4 Max (128GB) run gpt-oss 120B?
Yes. gpt-oss 120B runs on Apple M4 Max (128GB) at Q4_K_M (~62.4 GB of ~96 GB usable).
How much memory does gpt-oss 120B need?
Apple M4 Max (128GB) has room to spare. 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 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.
Sources
Memory figures are estimates. See methodology.