Home/Models/nvidia/llama-nemotron-embed-vl-1b-v2-fp8
llama-nemotron-embed-vl-1b-v2-fp8
nvidia/llama-nemotron-embed-vl-1b-v2-fp8
- kind
- fp8
- quant
- fp8 (8-bit)
- family
- llama
- modality
- sentence-similarity
- root model
- nvidia/llama-nemotron-embed-vl-1b-v2
- provider
- nvidia
- license
- other
- language
- multilingual
- context
- —
- library
- sentence-transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 487
- likes
- 11
- created
- —
- last modified
- 2026-06-11T07:48:28+00:00 (2026)
- huggingface
- https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2-fp8
- tags
- sentence-transformerssafetensorsllama_nemotron_vlfeature-extractionretrievalvisual document retrievalvlm embeddingpage image embeddingtext embeddingsemantic searchquestion-answering retrievalragtransformersquantizedsentence-similaritycustom_codemultilingualarxiv:2501.14818base_model:nvidia/llama-nemotron-embed-vl-1b-v2base_model:quantized:nvidia/llama-nemotron-embed-vl-1b-v2license:otherendpoints_compatiblemodeloptregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.