Will this model run on your hardware?
Can I run Qwen: Qwen3 235B A22B Instruct 2507 locally?
- 235B parameters (22B active, MoE)
- context up to 256K
- licence: apache-2.0
- Weights: Qwen/Qwen3-235B-A22B-Instruct-2507 · GGUF: unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 249.9 GB |
| Q6_K | 193.0 GB |
| Q5_K_M | 166.8 GB |
| Q4_K_M | 142.2 GB |
| Q3_K_M | 112.4 GB |
| Q2_K | 85.7 GB |
Run it locally
ollama run hf.co/unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q4_K_M
llama serve -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q4_K_M