Qwen3.6 35B-A3B
Qwen3.6 35B-A3B loads in 22 GB at Q4_K_M and decodes at the speed of its 3B active path, comfortably from 32 GB of memory — Macs included, starting at the MacBook Pro M5 Pro 48GB. Below is the memory math we ran for it, the cheapest card that fits, and the fastest machine we track.
How much memory does Qwen3.6 35B-A3B need?
Qwen3.6 35B-A3B is a 35B mixture-of-experts model (3B active per token) built for reasoning, coding, agents. The weights alone take 22 GB at Q4_K_M; add context and the OS, and it belongs in the 32 GB memory class. Every number below comes from the ModelFit engine — speeds are estimates, labeled est., because we do not benchmark hardware ourselves.
KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).
Which machines run Qwen3.6 35B-A3B?
Verdicts come from the same engine that powers our fit checker — memory capacity first, bandwidth for speed. How we compute these numbers · Hugging Face model card
Go deeper
More Qwen models
Frequently asked questions
How much memory does Qwen3.6 35B-A3B need?
22 GB for the Q4_K_M weights, plus ~0.3 GB of KV-cache at 16k context — about 22.3 GB total. Comfortable from 32 GB of VRAM or unified memory.
Does Qwen3.6 35B-A3B run on a Mac?
Yes — from the MacBook Pro M5 Pro 48GB (~39 tok/s est.). Unified memory means the RAM budget is the only limit.
What is the cheapest GPU for Qwen3.6 35B-A3B?
The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs Qwen3.6 35B-A3B comfortably — ~24 tok/s est. at ~$3,847 used (as of 2026-07-31).
Which Qwen3.6 35B-A3B quant should I pick?
The tracked Q4_K_M build at 22 GB is the one we recommend for most machines. Every published build, ranked by real GGUF file size rather than a formula, is on the quant comparison page linked below.
Cite this page
ModelFit: Qwen3.6 35B-A3B — specs, memory math and hardware verdicts. https://modelfit.io/models/qwen3.6-35b-a3b/ (dataset updated 2026-09-03, CC BY 4.0).