llama-nv-embed-reasoning-3b
nvidia/llama-nv-embed-reasoning-3b
- kind
- original
- quant
- bf16 (16-bit)
- family
- llama
- modality
- feature-extraction
- root model
- meta-llama/Llama-3.2-3B
- provider
- nvidia
- license
- cc-by-4.0
- language
- —
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 2,141
- likes
- 21
- created
- —
- last modified
- 2026-05-20T18:23:24+00:00 (2026)
- huggingface
- https://huggingface.co/nvidia/llama-nv-embed-reasoning-3b
- tags
- transformerssafetensorsllama_bidirecfeature-extractiontexttext-embeddingretrievalsemantic-searchtransformercustom_codedataset:xlangai/BRIGHTbase_model:meta-llama/Llama-3.2-3Bbase_model:finetune:meta-llama/Llama-3.2-3Blicense:cc-by-4.0text-embeddings-inferenceendpoints_compatibleregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.