33.7B- input
- $0.00
- output
- $0.00
- Context
- 33Ktokens
- Listed
- 3w ago
- Size
- 1Bparameters
Cost/1M tokens
Nemotron 3.5 Embed 1B is an embedding model trained by NVIDIA and distilled from the Nemotron-3.5-Embed-8B-BF16 teacher, with its language component initialized from Nemotron-3-Embed-1B-BF16. NVIDIA's launch announcement presents it as a multimodal embedding model for text and document-image retrieval in RAG applications. It is built for multilingual question-answering retrieval, turning text or document-page images into embeddings for semantic search and agentic RAG workflows.
How it compares
Size class
Tiny1BAn open-weight model under 5 billion parameters, small enough for phones, laptops and edge devices.
Open models of a similar size from other labs
Vs. your stack
Add the models you use to see how this one compares.
Sign inFrequently asked questions
Running locally
Nemotron 3.5 Embed 1B needs an estimated 1.2 GB at Q4, 1.7 GB at Q8 or 2.8 GB at FP16. All figures are estimates from the parameter count, covering weights plus about 15% and 0.5 GB for a short context.
Yes. Nemotron 3.5 Embed 1B fits on a 24 GB, 16 GB, 12 GB or 8 GB GPU at FP16, with an estimated 2.8 GB of VRAM.
Yes. At Q4 the model needs an estimated 1.2 GB, and assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits is 8 GB.
Privacy and data
Yes. Nemotron 3.5 Embed 1B has open weights, so you can self-host it for full control of your data.
Capabilities and specs
The context window of Nemotron 3.5 Embed 1B is 33K tokens (32,768), and its maximum output is 29K tokens (29,491).
Nemotron 3.5 Embed 1B reads text and images. Audio, video and PDFs are not listed as supported input modalities.
Quality and benchmarks
The closest alternatives, matched on model kind and release date with no comparable price, are LFM2.5-Embedding-350M by Liquid AI, Titan Text Embeddings V2 by Amazon at a blended price of $0.015 per 1M tokens, and Titan Embeddings G1 - Text by Amazon at $0.075 per 1M tokens.
LFM2.5-Embedding-350MNemotron 3.5 Embed 1B vs LFM2.5-Embedding-350MTitan Text Embeddings V2Nemotron 3.5 Embed 1B vs Titan Text Embeddings V2Titan Embeddings G1 - TextNemotron 3.5 Embed 1B vs Titan Embeddings G1 - Text
Versions and lineage
Nemotron 3.5 Embed 1B was released on October 21, 2026, costs $0.00 input and $0.00 output per 1M tokens and has a 33K token (32,768) context. Nemotron 3.5 ASR Streaming Multilingual 0.6B was released on August 13, 2026, and costs $3.33 input and $0.00 output per 1M tokens.
Nemotron 3.5 ASR Streaming Multilingual 0.6BNemotron 3.5 Embed 1B vs Nemotron 3.5 ASR Streaming Multilingual 0.6B
Licensing and access
Nemotron 3.5 Embed 1B is open weights.
The Nemotron 3.5 Embed 1B weights can be downloaded from the Hugging Face repository nvidia/Nemotron-3.5-Embed-1B-BF16.
Basics
Nemotron 3.5 Embed 1B was made by NVIDIA and was first listed on OpenRouter on October 21, 2026.
Yes. Nemotron 3.5 Embed 1B has open weights.
Generated from Vertical Tabs data, updated November 2, 2026.
More in Nemotron
33.7B8BNemotron 3.5 Embed 8B
8BNemotron 3.5 Rerank 8B
Nemotron 3.5 Super VL
120BNemotron 3.5 Super 120B A12B
0.6BNemotron 3.5 ASR Streaming Multilingual 0.6B
30BNemotron 3.5 Lightning
1BNemotron 3 Embed 1B
550BNemotron 3 Ultra
4.3BNemotron 3.5 Content Safety
30BNemotron 3 Nano Omni
30B
Discussion
No comments yet
Be the first to share your thoughts.