Can I Run Qwen3-Coder 80B-A3B (MoE) on Apple M2 Max?

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes. Qwen3-Coder 80B-A3B (MoE) needs 48.3 GB at Q4_K_M and the Apple M2 Max has 96 GB, leaving about 47.7 GB of headroom, at roughly 59 tok/s (estimated) with room for up to 128K of context.

The numbers

Model	Qwen3-Coder 80B-A3B (MoE)
Parameters	80B/3B active
Quantization	Q4_K_M
VRAM needed	48.3 GB
Apple M2 Max VRAM	96 GB
Verdict	Runs
Max context	128K
Estimated speed	~59 tok/s

What to do next

Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Running Qwen3-Coder 80B-A3B (MoE) on this card:

Apple Mac Studio M2 Max

96 GB VRAM · 40 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

Buy vs. rent Qwen3-Coder 80B-A3B (MoE)

Buy the GPU

~$3,499

Apple M2 Max · MSRP

Rent by the hour

from $0.77/hr

A100 (80 GB) class