Local inference
Ready to connect
LM Studio
Configure your local server
Configuration
Models0
Name
API endpoint
The address of your running local model server.
Harness access
0 of 7 supported harnesses enabled
4 models available from Local AI.
Qwen3 Coder 30B
qwen3-coder-30b-a3b-instruct
GPT OSS 20B
openai/gpt-oss-20b
Qwen2.5 Coder 32B
qwen2.5-coder-32b-instruct
Devstral 24B
mistralai/devstral-small-24b
Sample models shown for this demo.