Qwen3 235B A22B

Flagship open-weight Qwen3 MoE model often chosen for serious reasoning, coding, multilingual work, and agent experiments.

Alibaba Qwen · Qwen

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedAugust 2026SourcesHugging Face model card, Qwen GitHub, Qwen organization on Hugging Face

Model checkpoints, context windows, provider support, local runtime compatibility, and license terms can change quickly. Verify the exact model card before production or commercial use.

Best for

Builders testing frontier-style open-weight reasoning and coding in hosted or multi-GPU environments.

Who should use it

Builders testing frontier-style open-weight reasoning and coding in hosted or multi-GPU environments.
Teams with access to hosted inference or server-class deployment paths.
Developers evaluating coding assistant, repo-editing, and code review workflows.
Teams testing tool-use, agentic planning, and multi-step workflow behavior.

Common workflows

Reasoning, coding, multilingual chat, agents
reasoning workflows
coding workflows
multilingual workflows
agents workflows

Deployment and hardware notes

Usually a server or multi-GPU model; use quantized builds or hosted inference for practical testing.

License and usage notes

Apache 2.0. Open weights. Verify the exact model card and license terms for the checkpoint or hosted provider you use.

Strengths

Open weights model option for Qwen workflows.
Builders testing frontier-style open-weight reasoning and coding in hosted or multi-GPU environments.
Tracked as Frontier 2026 in the OpenSourcesAI model directory.

Limitations

Too large for most consumer machines; check current benchmark leaderboards and provider support before production use.
Usually a server or multi-GPU model; use quantized builds or hosted inference for practical testing.
Context window and limits: 40,960 tokens.
Verify the exact model card, provider docs, license, and serving support before production use.

Will Qwen3-235B-A22B run on your machine?

Qwen3-235B-A22B is 235B parameters and needs 141.5 GB of VRAM at Q4_K_M — 140 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

Quantization	Weights	Needs (with overhead)	Quality
Q4_K_M	140 GB	141.5 GB	good
Q8_0	236 GB	237.5 GB	high

Fit on common hardware at Q4_K_M

Hardware	Memory the model can use	System RAM	Verdict
CPU Only	None (CPU only)	16 GB	Too large
RTX 4060 Laptop	8 GB	16 GB	Too large
RTX 3060 (12GB)	12 GB	32 GB	Too large
RTX 4060 Ti (16GB)	16 GB	32 GB	Too large
RTX 3090	24 GB	64 GB	Too large
Apple Silicon (Unified Memory) 36 GB	27 GB of 36 GB	36 GB	Too large
RTX 5090	32 GB	64 GB	Too large
Apple Silicon (Unified Memory) 48 GB	36 GB of 48 GB	48 GB	Too large
Apple Silicon (Unified Memory) 64 GB	48 GB of 64 GB	64 GB	Too large
Apple Silicon (Unified Memory) 96 GB	72 GB of 96 GB	96 GB	Too large
Apple Silicon (Unified Memory) 128 GB	96 GB of 128 GB	128 GB	Too large
Apple Silicon (Unified Memory) 192 GB	144 GB of 192 GB	192 GB	Comfortable

Comfortable means VRAM clears the requirement by 2 GB or more. Tight means it covers the requirement with no margin. CPU offload means the model does not fit in VRAM but system RAM is at least 1.6× the weights, so it will run at reduced speed — expect roughly 1–5 tokens per second. Figures are weights plus a fixed runtime overhead and exclude KV-cache growth, which scales with context length.

Apple Silicon shares one pool of memory between the system and the GPU, so a model cannot use all of it. These rows apply the same 75% usable fraction the Compatibility Checker uses, which is why a 36 GB Mac is graded on less than 36 GB.

Check Qwen3-235B-A22B against your exact hardware How these verdicts are calculated

VRAM fit by quantization level

Enter your GPU VRAM below to see which quantization of Qwen3 235B A22B fits and get the Ollama run command.

Frontier-model verification note

This page is written to stay accurate as of the latest available 2026 public model information. Availability, licenses, context windows, API support, pricing, benchmark standing, and local-serving support can change quickly. Verify the official model card, provider docs, and license before using this model in production or commercial workflows.