Alibaba (Qwen team) · open weights · updated July 2026

Qwen3-Coder (480B-A35B)

Parameters
480B / 35B active
Context window
256K tokens (1M with extrapolation)
License
Apache 2.0
Modalities
text
Released
2025-07-22

Qwen3-Coder is Alibaba's dedicated agentic-coding model: 480B total parameters with 35B active, 256K native context extrapolating to 1M, and 69.6% on SWE-bench Verified — for much of 2025–26 the strongest pure-coding score in open weights under Apache 2.0.

It ships with Qwen Code (a CLI adapted from Gemini CLI) and slots into Claude Code-style agent workflows. The smaller 30B-A3B variant brings the same recipe to single-GPU setups, making the Coder line the most complete open-weight coding stack from one vendor.

Qwen3-Coder specifications

VendorAlibaba (Qwen team) (China)
ArchitectureMixture-of-Experts, code-specialized
Total parameters480B
Active parameters35B
Context window256K tokens (1M with extrapolation)
Modalitiestext
LicenseApache 2.0 — permissive, patent-granting, free for commercial use
Release date2025-07-22
WeightsHugging Face · GitHub

Benchmarks and reported results

BenchmarkResultNote
SWE-bench Verified69.6%

Running Qwen3-Coder locally

480B total / 35B active: about 270GB at 4-bit. Widely hosted; locally it wants a multi-GPU node, though smaller Qwen3-Coder variants (30B-A3B) run on a single 24GB GPU.

What Qwen3-Coder is best for

  • Agentic coding under the cleanest enterprise license (Apache 2.0)
  • Repository-scale refactoring (256K–1M context)
  • Single-GPU coding via the 30B-A3B variant

Frequently asked questions

Is Qwen3-Coder better than general models at coding?

On pure software-engineering benchmarks it led the Apache-2.0 field with 69.6% SWE-bench Verified. Newer generalists (Kimi K2.5, GLM-5.2, DeepSeek V4) have since matched or passed it, but it remains a focused, widely-hosted coding specialist with an unbeatable license.