8K Downloads

qwen/
qwen3-coder-30b
30B
qwen3moe

A powerful 30B MoE coding model from Alibaba Qwen, joining its larger 480B counterpart

Tool use

Last Updated1 day ago
README

Qwen3 Coder 30B

Specialized coding model with native support for 256K context length

MoE model with 3.3B activated weights out of 30.5B total parameters, 128 experts with 8 active

Excels at agentic coding, browser automation, and repository-scale code understanding

Advanced tool calling capabilities supporting platforms like Qwen Code and CLINE

Optimized for coding tasks with significant performance improvements in agentic workflows

Note: This model does not support thinking mode and will not generate <think></think> blocks

sources

The underlying model files this model uses

When you download this model, LM Studio picks the source that will best suit your machine (you can override this)

config

Custom configuration options included with this model

Repeat Penalty
1.05
Temperature
0.7
Top K Sampling
20
Top P Sampling
0.8