Qwen released Qwen3 Coder 30B A3B Instruct on July 31, 2025. The registry currently records it as open weights.
Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.
This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.
The structured profile below stays connected to the canonical model record, including its architecture, parameters, papers, benchmarks, media, licence, and source links as those fields are enriched.
Model publication
Qwen
Qwen3 Coder 30B A3B InstructOpen the source for Qwen3 Coder 30B A3B Instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.
- Licence
- apache-2.0
- Architecture
- Qwen3MoeForCausalLM
- Parameters
- 30.5B
- Context
- 262.1K tokens
- Artifact format
- safetensors
- Quantization
- native BF16
- Download size
- 57 GB

Hardware to run it (inference, estimated)
69 GB VRAM minimum · 86 GB recommended · 86 GB system RAM · 57 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.