Nemotron-3-Embed-8B-BF16
Image Generationnvidia · nvidia · v3 · released
About
wer
Architecture
- Type
- encoder
- Parameters
- 1.0B
- Active
- 2.0B
- Layers
- 2
- Hidden dim
- 2
wkjher
Memory
- Weights (BF16)
- 2.00 GB
- Activation estimate
- 0.00 GB
Pricing
Free — open weights
Self-host on your own GPU. The calculator surfaces GPU-hours cost on the hardware page instead of an API price.
Provenance
- Hugging Face
- nvidia/Nemotron-3-Embed-8B-BF16
sentence-transformerssafetensorsministral3feature-extractiontexttext-embeddingsretrievalsemantic-search