Qwen

Qwen3-Coder-Next

80B-class Qwen coding model with native 262,144-token context, tuned for IDE and CLI agent workflows.Apache 2.0Hugging Face

No server in stock right now has the 178 GB this model needs for inference.

GPU memory it needs

From model cards and vendor documentation. Lower precision needs less memory, with slightly lower quality. Estimates are marked.

What you want to do	Precision	Minimum	Basis
Run the model Arithmetic: 148.4 GiB BF16 weights x 1.2 runtime overhead. No GB figure published; the model card's serving example uses tensor parallel on 4 GPUs at 256K context and suggests reducing context length on OOM.	BF16, full	178.1 GB	Estimated