Qwen3-Coder-480B-A35B-Instruct
by Qwen
480B params · text-generation · 1.3k likes · 69.2k downloads
Qwen3-Coder-480B-A35B-Instruct is a 480B parameter model. At Q4 quantization it requires 240GB of VRAM. It requires a GPU with at least 240GB of VRAM.
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Novita | 64 tok/s | ||
| Hyperbolic | 66 tok/s | ||
| Together AI | 58 tok/s |