← All models View on HuggingFace →
Qwen: Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct
Tool useJSONStreaming
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...
Pricing
Input
$0.07 / 1M
Output
$0.27 / 1M
Specs
Context
160,000 tokens
Input
text
Output
text
Knowledge cutoff: 2025-06-30
Released: 2025-07
Supported parameters
frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
1,962,787 downloads/mo
1,085 likes
apache-2.0 text-generation