Qwen3-Coder 480B-A35B (MoE) — VRAM, Speed & Local Setup

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 8 lipca 2026

Model library → Qwen3-Coder → Qwen3-Coder 480B-A35B (MoE)

The flagship dedicated coder: 480B total with 35B active parameters per token and 256K native context (extendable to ~1M). Holds state-of-the-art among open models on SWE-bench Verified and agentic coding at release, with Qwen positioning it comparable to Claude Sonnet 4. Datacenter / multi-GPU only — reach for the 80B-A3B when you need single-GPU deployment.

Qwen3-Coder 480B-A35B (MoE) needs about 291 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

Parameters480 Billion (35B active)
Context window256,000
ArchitectureMixture-of-Experts
ProviderAlibaba Cloud
LicenceApache 2.0
Specified atQ4_K_M
System RAM512 GB
Record updated2026-07-08

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). Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. 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.

QuantBits/weightWeightsVRAM neededEst. speedFit on 24 GB
Q2_K2.63157.8 GB159.6 GB—Won't fit
Q3_K_M3.41204.6 GB206.4 GB—Won't fit
Q4_K_M4.83289.8 GB291.6 GB—Won't fit
Q5_K_M5.67340.2 GB342 GB—Won't fit
Q6_K6.56393.6 GB395.4 GB—Won't fit
Q8_08.50510 GB511.8 GB—Won't fit
F1616.00960 GB961.8 GB—Won't fit

Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.

Buy This HardwareApple Mac Studio M3 Ultra — 512 GB VRAM · 60 W board powerDeploy in the Cloud NowRunPod

or compare on Vast.ai

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 480B-A35B (MoE) is the Apple M3 Ultra (512 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.
Apple Mac Studio M3 Ultra
512 GB VRAM · 60 W board power
Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.
Sprawdź cenę na Amazon

How to Run Qwen3-Coder 480B-A35B (MoE)

Install Ollama, then run:

ollama run qwen3-coder:480b-a35b

Weights on Hugging Face: Qwen/Qwen3-Coder-480B-A35B-Instruct.

Published Benchmark Scores

Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.

BenchmarkScoreProvenance
SWE-bench Verified69.6 %reported · Qwen (open-model SoTA at release)

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

Can I Run Qwen3-Coder 480B-A35B (MoE) on My GPU?

Other Qwen3-Coder Sizes

Qwen3-Coder 480B-A35B (MoE) — Frequently Asked Questions

How much VRAM does Qwen3-Coder 480B-A35B (MoE) need?
About 291 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 480B-A35B (MoE) run on an RTX 4090 (24 GB)?
No. Qwen3-Coder 480B-A35B (MoE) needs about 291 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 480B-A35B (MoE) locally?
Install Ollama and run `ollama run qwen3-coder:480b-a35b`. 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