Qwen3-235B-A22B
by Qwen
235B params · text-generation · 1.1k likes · 700.0k downloads
Qwen3-235B-A22B is a 235B parameter model. At Q4 quantization it requires 118GB of VRAM. It fits on H200 SXM 141 GB (29 tok/s), M2 Ultra 192GB (2 tok/s) but performance may be limited.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Novita | 11 tok/s | ||
| Nscale | 22 tok/s |
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| H200 SXM 141 GB | 141GB | 29 tok/s | tight |
| M2 Ultra 192GB | 192GB | 2 tok/s | tight |