Browse docs

DOCUMENTATION

Supported models

These models have been tested with TypeLLM on a live SGLang GPU server.

ModelThinking
Qwen/Qwen3.8-27BOn / off
Qwen/Qwen3.5-0.8B / 4B / 9BOn / off
openbmb/MiniCPM5-1BOn / off
inclusionAI/Ling-mini-2.0Off only
inclusionAI/Ring-mini-2.0Always on

Image input has been tested with Qwen/Qwen3.8-27B. See Image input.

Other sizes in the Qwen3.5 and Qwen3.8 families are expected to be compatible. If the server's tokenizer path is unavailable locally, set tokenizer= to the matching Hugging Face ID or local tokenizer directory.