Model overview
What this model is for
Pathumma-llm-vision-3.0.0-re is a 2-billion-parameter image-text-to-text model intended for applications that combine visual and textual input. Its advertised modalities are image and text, and the available model metadata categorizes it for vision use. A developer could evaluate it for tasks such as interpreting images alongside prompts, answering questions about visual content, or generating text conditioned on an image, subject to validating the model’s actual behavior in the intended deployment environment. The supplied material does not provide an advertised context window, inference speed benchmark, pricing, supported runtime, quantization details, or implementation requirements. It also does not include task-specific accuracy results, so suitability for production workloads cannot be determined from this information alone. Licensing terms and any usage restrictions are not available in the supplied material and should be checked on the Hugging Face model page before distribution or commercial use. The model is hosted by the nectec organization on Hugging Face, which is the listed source and official URL.