qwen
235B parameters
Commercial OK

Qwen 3 235B-A22B

Qwen 3 flagship MoE. 235B total / 22B active per token, with built-in 'thinking' and 'non-thinking' modes that trade speed for reasoning depth at inference time. Best open-weight reasoning model for many tasks.

License: Apache 2.0·Released Apr 29, 2025·Context: 131,072 tokens

Overview

Qwen 3 flagship MoE. 235B total / 22B active per token, with built-in 'thinking' and 'non-thinking' modes that trade speed for reasoning depth at inference time. Best open-weight reasoning model for many tasks.

Strengths

  • Switchable thinking mode
  • Apache 2.0
  • Top-tier reasoning

Weaknesses

  • Needs 160GB+ VRAM at Q4
  • Multi-GPU only on consumer rigs

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M142.0 GB160 GB
Q5_K_M167.0 GB190 GB

Get the model

Ollama

One-line install

ollama run qwen3:235bRead our Ollama review →

HuggingFace

Original weights

huggingface.co/Qwen/Qwen3-235B-A22B

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Qwen 3 235B-A22B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step up
More capable — bigger memory footprint
No verdicted models in the next tier up yet.

Frequently asked

What's the minimum VRAM to run Qwen 3 235B-A22B?

160GB of VRAM is enough to run Qwen 3 235B-A22B at the Q4_K_M quantization (file size 142.0 GB). Higher-quality quantizations need more.

Can I use Qwen 3 235B-A22B commercially?

Yes — Qwen 3 235B-A22B ships under the Apache 2.0, which permits commercial use. Always read the license text before deployment.

What's the context length of Qwen 3 235B-A22B?

Qwen 3 235B-A22B supports a context window of 131,072 tokens (about 131K).

How do I install Qwen 3 235B-A22B with Ollama?

Run `ollama pull qwen3:235b` to download, then `ollama run qwen3:235b` to start a chat session. The default quantization is Q4_K_M.

Source: huggingface.co/Qwen/Qwen3-235B-A22B

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.