Qwen logo

Qwen3-Next 80B-A3B

Qwen3-Next 80B-A3B loads in 50.4 GB at Q4_K_M and decodes at the speed of its 3B active path, comfortably from 96 GB of memory — Macs included, starting at the MacBook Pro M5 Max 128GB. Below is the memory math we ran for it, the cheapest card that fits, and the fastest machine we track.

PARAMETERS
80B (3B active)
FORMAT
Q4_K_M
MIN MEMORY
72 GB
BEST FOR
Chat, Coding, Long Context

How much memory does Qwen3-Next 80B-A3B need?

Qwen3-Next 80B-A3B is a 80B mixture-of-experts model (3B active per token) built for chat, coding, long context. The weights alone take 50.4 GB at Q4_K_M; add context and the OS, and it belongs in the 96 GB memory class. Every number below comes from the ModelFit engine — speeds are estimates, labeled est., because we do not benchmark hardware ourselves.

Weights (Q4_K_M)
50.4 GB
+ KV cache (16k)
~0.4 GB
Total at 16k
~50.8 GB
Comfortable from
96 GB

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-Next 80B-A3B?

Cheapest GPU
~17 tok/s est. — ~$3,847 used (as of 2026-07-31)
Fastest
~83 tok/s est.
Runs on a Mac?
~44 tok/s est.

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

Every Qwen3-Next 80B-A3B quant by real GGUF file sizeAlso tracked: Qwen3-Next 80B-A3B (Q8) (Q8_0, 84.8 GB, min 128 GB)

More Qwen models

Frequently asked questions

How much memory does Qwen3-Next 80B-A3B need?

50.4 GB for the Q4_K_M weights, plus ~0.4 GB of KV-cache at 16k context — about 50.8 GB total. Comfortable from 96 GB of VRAM or unified memory.

Does Qwen3-Next 80B-A3B run on a Mac?

Yes — from the MacBook Pro M5 Max 128GB (~44 tok/s est.). Unified memory means the RAM budget is the only limit.

What is the cheapest GPU for Qwen3-Next 80B-A3B?

The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs Qwen3-Next 80B-A3B comfortably — ~17 tok/s est. at ~$3,847 used (as of 2026-07-31).

Which Qwen3-Next 80B-A3B quant should I pick?

The tracked Q4_K_M build at 50.4 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-Next 80B-A3B — specs, memory math and hardware verdicts.
https://modelfit.io/models/qwen3-next-80b-a3b/ (dataset updated 2026-09-03, CC BY 4.0).