Local AI Advisor

Can MacBook Pro M5 Max 36 GB run Qwen3.5 122B-A10B?

36 GB unified · 460 GB/s memory bandwidth · Qwen3.5 122B-A10B has 125B parameters (10B active per token).

Short answer

No. It doesn't fit in memory.

Needs ≈53 GB but only ≈28 GB is available after the OS, other apps and Open WebUI.

Why it doesn’t fit

Even its smallest practical version (3-bit) needs about 53 GB for the model, its context memory and the runtime. After macOS (≈3.6 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), MacBook Pro M5 Max 36 GB has about 28 GB left, so it’s 24 GB short.

Ways to make it work

The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.

Different tool, context size or workload?

These pages use typical settings. The full check models your exact setup.