Qwen3 Coder Next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment. The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit <think> blocks, simplifying integration for production coding agents.

Licence

apache-2.0

Architecture

Qwen3NextForCausalLM

Parameters

79.7B

Context

262.1K tokens

Artifact format

safetensors

Quantization

native BF16

Download size

148 GB

Hardware to run it (inference, estimated)

179 GB VRAM minimum · 223 GB recommended · 223 GB system RAM · 149 GB storage

Estimated from parameter count and stored precision; verify against the selected runtime and context length.

Benchmarks

No benchmark observation recorded for this model.