Image-Text-to-Text
Safetensors
qwen3_vl
vision
multilingual
indic-languages
merged
translation
document-understanding
fine-tuned
conversational
Instructions to use mashriram/Sarvam-1-VL-4B-Instruct-VLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
Ctrl+K