NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)
- by nvidia
- nvidia/llama-nemotron-rerank-vl-1b-v2:free
Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG...
What the numbers mean
- Context window10,240 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 7,700 words, or 15 pages.
- Max output9,216 tokens
- The longest single reply it can write: about 6,900 words.
- Input priceFree
- What you pay for everything the model reads. A 1,000-word prompt costs nothing.
- Output priceFree
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs nothing.
- Modalitiestext, image in, rerank out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.