Runs On
What it takes to serve Nemotron-3-Embed-1B-BF16 (1.1B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
SAVRN's Notes on Nemotron-3-Embed-1B-BF16
Embedding is where a retrieval stack starts, and this is NVIDIA's model for that step: text in, vectors out, evaluated across 34 languages. At 16-bit the weights are 2.3 GB and the run needs 2.7 GB, so the cheapest setup we track, one 192 GB MI300X at $1.85 per hour on demand, barely notices it. Nobody buys a card for this. You park it beside the generation model it feeds. The 262,144-token context length changes how you chunk, since a whole filing can go in as one input.
The license reads as other, with no summary in our file, so read NVIDIA's terms before commercial use. It is derived from Ministral-3-3B-Instruct-2512, so check whether that base carries conditions of its own. Access is open, and no Index host prices it by the token today, which leaves the hour rate and the power as the whole cost.
SAVRN Research, 2026-09-18
Model Card
NVIDIA Nemotron 3 Embed Nemotron-3-Embed-1B-BF16 is a versatile text embedding model trained by NVIDIA and optimized for retrieval and semantic similarity tasks. It provides strong multilingual and cross-lingual retrieval capabilities and is designed to serve as a foundational component in text-based Retrieval-Augmented Generation (RAG) systems. This model was evaluated across 34 languages: English, Arabic, Assamese, Bengali, Bulgarian, Chinese, Danish, Dutch, Finnish, French, German, Hindi, Hinglish, Indonesian, Italian, Japanese, Korean, Malay, Marathi, Nepali, Norwegian, Persian, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Ukrainian, Urdu, Vietnamese.…
Excerpt from the card by NVIDIA, licensed other.
Configuration
- Architecture
- Ministral3Model
- Context length (tokens)
- 262,144
- Layers
- 16
- Hidden size
- 2,048
- Feed-forward size
- 6,144
- Attention heads
- 24
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 131,072
- RoPE base
- 1e+06
- Model type
- ministral3
Identity and Version
- Repository
- nvidia/Nemotron-3-Embed-1B-BF16
- Publisher
- NVIDIA
- Task
- Sentence similarity
- Modality
- Text
- Library
- sentence-transformers
- Parameters
- 1.1B parameters
- Languages
- en, ar, as, bn, bg, zh, da, nl
- Revision
- c0c9fea93ea424587517f2c59e20db9f1d6bf615
- First published
- 2026-07-14
- Last updated
- 2026-08-27
Files and Weights
15 files, 2.3 GB in total. The weights are 1 file totalling 2.3 GB in safetensors.
Weights1 file · 2.3 GB
Configuration6 files · 11.0 KB
Tokenizer2 files · 17.1 MB
Documentation5 files · 67.8 KB
Repository1 file · 1.6 KB
Every file
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 2.3 GB
Built From
- Derived from
mistralai/Ministral-3-3B-Instruct-2512
- Described by
arXiv:2407.14679
- Described by
arXiv:2502.13595
Memory Requirements
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Nemotron-3-Embed-1B-BF16
How much GPU memory does Nemotron-3-Embed-1B-BF16 need?
About 2.7 GB at 16-bit and 0.7 GB at 4-bit: the weights (1.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Nemotron-3-Embed-1B-BF16 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What license is Nemotron-3-Embed-1B-BF16 released under?
other, as its publisher declares it. Read the license text before commercial use.
What is Nemotron-3-Embed-1B-BF16's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.
Similar Models
12/11/2024: Release of Technical Report - 12/04/2024: Release of snowflake-arctic-embed-l-v2.0 and snowflake-arctic-embed-m-v2.0 our newest models with multilingual workloads in mind. Snowflake arctic-embed-l-v2.0 is the newest addition to the suite of embedding models Snowflake has released optimizing for retrieval performance and inference efficiency. Arctic Embed 2.0 introduces a new standard for multilingual embedding models, combining high-quality multilingual text retrieval without sacrificing performance in English. Released under the permissive Apache 2.0 license, Arctic Embed 2.0 is ideal for applications that demand reliable, enterprise-grade multilingual search and retrieval at…
Open weights
apache-2.0
568M parameters
8,194 tokens
sentence-transformers
gte-Qwen2-1.5B-instruct is the latest model in the gte (General Text Embedding) model family. The model is built on Qwen2-1.5B LLM model and use the same training data and strategies as the gte-Qwen2-7B-instruct model. The model incorporates several key advancements: - Integration of bidirectional attention mechanisms, enriching its contextual understanding. - Instruction tuning, applied solely on the query side for streamlined efficiency - Comprehensive training across a vast, multilingual text corpus spanning diverse domains and scenarios. This training leverages both weakly supervised and supervised data, ensuring the model's applicability across numerous languages and a wide array of…
Open weights
apache-2.0
1.8B parameters
131,072 tokens
sentence-transformers
This model was presented in the paper Training Sparse Mixture Of Experts Text Embedding Models. nomic-embed-text-v2-moe is a SoTA multilingual MoE text embedding model that excels at multilingual retrieval: Transformer-based text embedding models have improved their performance on benchmarks like MIRACL and BEIR by increasing their parameter counts. However, this scaling approach introduces significant deployment challenges, including increased inference latency and memory usage. These challenges are particularly severe in retrieval-augmented generation (RAG) applications, where large models' increased memory requirements constrain dataset ingestion capacity, and their higher latency…
Open weights
apache-2.0
475M parameters
sentence-transformers
This is a port of the LaBSE model to PyTorch. It can be used to map 109 languages to a shared vector space. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Have a look at LaBSE for the respective publication that describes LaBSE.
Open weights
apache-2.0
471M parameters
512 tokens
sentence-transformers
Model · Sentence similarity
Zulfah
Semantic-Lite-2 is a lightweight multilingual sentence embedding model that produces 256-dimensional semantic vectors. It is designed for semantic search, sentence similarity, clustering, retrieval, and retrieval-augmented generation (RAG) tasks. The model is built on top of the Spark-X2.5-1.7B backbone using a frozen-backbone plus trainable-projection-head approach. The 256-dimensional output keeps vector storage compact while preserving strong retrieval quality. Vectors are L2-normalized, so cosine similarity is computed as a simple dot product. Evaluated on 500 Indonesian NLI evaluation pairs (retrieval task, chance level 0.2%): Cross-lingual evaluation (10 languages, 20 pairs per…
Open weights
apache-2.0
460M parameters
1,048,576 tokens
transformers
We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the transformer++ encoder backbone (BERT + RoPE + GLU). The gte-v1.5 series achieve state-of-the-art scores on the MTEB benchmark within the same model size category and prodvide competitive on the LoCo long-context retrieval tests (refer to Evaluation). We also present the gte-Qwen1.5-7B-instruct, a SOTA instruction-tuned multi-lingual embedding model that ranked 2nd in MTEB and 1st in C-MTEB. Models for Multilingual Text Retrieval](https://arxiv.org/pdf/2407.19669) Use the code below to get started with the model. It is…
Open weights
apache-2.0
434M parameters
8,192 tokens
transformers
