Vision-language generation

Family-owned implementations of the vision-language generation task interface.

Classification follows the Hugging Face task taxonomy. See the Hugging Face Vision-language generation task page for the ecosystem-level task definition.

Model families

Model family	Declared recipes	Exact checkpoint examples	Runtime CLI
`deepseek_ocr`	3	`deepseek-ai/DeepSeek-OCR-2`	`trtmc run`
`internvl`	4	`OpenGVLab/InternVL3-2B-hf` `OpenGVLab/InternVL3-8B-hf`	`trtmc run`
`lance`	1	`bytedance-research/Lance`	`trtmc run`
`locateanything`	1	`nvidia/LocateAnything-3B`	`trtmc run`
`phi4_multimodal`	1	`microsoft/Phi-4-multimodal-instruct`	`trtmc run`
`qwen_vl`	4	`Qwen/Qwen2.5-VL-3B-Instruct` `Qwen/Qwen3-VL-2B-Instruct`	`trtmc run`