Qwen3-235B-A22B
Qwen3-235B-A22B is an open-weights language model from Qwen, released April 28, 2025. It has 235B parameters (mixture-of-experts, 22B active). The context window is 128K tokens. On the Epoch Capabilities Index it scores 138.4, rank 130 of 256 rated models. API price: $0.7 input / $2.8 output per million tokens.
Check it against your own PC →
Can you run Qwen3-235B-A22B locally?
The smallest common GPU it runs on is 32 GB of VRAM (with 32 GB of RAM): IQ1_M, GPU + experts in RAM, roughly 18 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Runs · GPU + CPU experts | IQ1_M (experimental) | 31.2 GB | 24.0 GB | ~18 |
Ready-made quantizations on Hugging Face: unsloth/Qwen3-235B-A22B-GGUF · Qwen/Qwen3-235B-A22B-GGUF · unsloth/Qwen3-235B-A22B-128K-GGUF · DevQuasar/Qwen.Qwen3-235B-A22B-GGUF · lmstudio-community/Qwen3-235B-A22B-GGUF · QuantFactory/Homunculus-GGUF
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 68.9% |
| GPQA Diamond | 63.5% |
| Aider Polyglot | 59.6% |
| SimpleBench | 17.2% |
Links
Hugging Face: Qwen/Qwen3-235B-A22B · Epoch AI benchmarks
Models with a similar score
Gemini 2.5 Flash (Sep 2025) · Claude Sonnet 4 · Gemma 4 26B A4B · Mistral Medium 3.5 · Gemini 2.5 Flash (May 2025) · Kimi K2 (Jul 2025) · o1 · Claude 3.7 Sonnet
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash