Nemotron 3.5 Embed 1B
Nemotron 3.5 Embed 1B is a released general LLM work model with open-weight; evaluate it while provider pricing coverage matures.
- Family
- NV-Embed
- Released
- 2026-10-20
- Context
- 32K
- Parameters
- 1.55B
- Architecture
- Encoder Only
- Specialization
- embedding
- Openness
- Open weights
- License
- OpenMDW 1.1Permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
No tracked provider pricing is available yet.
About
Nemotron 3.5 Embed 1B is an open-weight NVIDIA multimodal, multilingual embedding model for question-answering retrieval with 1.55 billion parameters and a 32,768-token context. It embeds document pages as text, page images or both (tables, charts, infographics) and takes text queries, for vision RAG and semantic search. Text retrieval was evaluated in 34 languages and image retrieval in 18. It pairs a Pixtral vision encoder from Ministral 3 3B with a language model from Nemotron 3 Embed 1B. Weights are under OpenMDW-1.1 for commercial use.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
nvidia/Nemotron-3.5-Embed-1B-BF16No tracked provider pricing is available yet.