Qwen3-Coder 80B-A3B (MoE) — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated February 5, 2026

Model library → Qwen3-Coder → Qwen3-Coder 80B-A3B (MoE)

Efficiency flagship. 80B total with only 3B active parameters per forward pass. Scores 76.4 on SWE-bench Pro — comparable to Claude Sonnet 4.5 — while staying light enough to self-host on a single high-VRAM card. Beats DeepSeek V3.2 on most coding benchmarks.

Qwen3-Coder 80B-A3B (MoE) needs about 49 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters80 Billion (3B active)
Context window128,000
ArchitectureMoE
ProviderAlibaba Cloud
LicenceApache 2.0
Specified atQ4_K_M
System RAM32 GB
Record updated2026-02-05

Licence

Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K26.3 GB27.1 GB~29 tok/s (est.)Offloads to system RAM (slow)
Q3_K_M34.1 GB34.9 GB~27 tok/s (est.)Offloads to system RAM (slow)
Q4_K_M48.3 GB49.1 GB~24 tok/s (est.)Offloads to system RAM (slow)
Q5_K_M56.7 GB57.5 GB—Won't fit
Q6_K65.6 GB66.4 GB—Won't fit
Q8_085.0 GB85.8 GB—Won't fit
F16160.0 GB160.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Qwen3-Coder 80B-A3B (MoE) VRAM calculator.

Buy This HardwareApple MacBook Pro M5 Pro — 64 GB VRAM · 30 W board powerDeploy in the Cloud NowNVIDIA A100 80GB on RunPod — from $1.39/hr · rate checked 2026-07

or compare on Vast.ai from $0.77/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Qwen3-Coder 80B-A3B (MoE) is the Apple M5 Pro (64 GB).

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.
Apple MacBook Pro M5 Pro
64 GB VRAM · 30 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run Qwen3-Coder 80B-A3B (MoE)

Install Ollama, then run:

ollama run qwen3-coder:80b-a3b-q4

Weights on Hugging Face: Qwen/Qwen3-Coder-80B-A3B-Instruct.

Best for: coding, agents, swe bench, repo tasks.

Can I Run Qwen3-Coder 80B-A3B (MoE) on My GPU?

Other Qwen3-Coder Sizes

Qwen3-Coder 80B-A3B (MoE) — Frequently Asked Questions

How much VRAM does Qwen3-Coder 80B-A3B (MoE) need?
About 49 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Qwen3-Coder 80B-A3B (MoE) run on an RTX 4090 (24 GB)?
No. Qwen3-Coder 80B-A3B (MoE) needs about 49 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Qwen3-Coder 80B-A3B (MoE) locally?
Install Ollama and run `ollama run qwen3-coder:80b-a3b-q4`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Qwen3-Coder come in?
Qwen3-Coder 8B (6 GB), Qwen3-Coder 80B-A3B (MoE) (49 GB), Qwen3-Coder 480B-A35B (MoE) (291 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Qwen3-Coder models | VRAM calculator | Check your own hardware