nvidia / sentence-similarity updated 2 weeks ago

Nemotron-3-Embed-1B-BF16

Name: Nemotron-3-Embed-1B-BF16
Author: nvidia

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, Chi...

Params

1.1 B

Context

262,144

Downloads 30d

456 K

Likes

128

Licence: other Not gated SAFETENSORS 34 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (4 recorded)

456 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	2.3 GB	3.2 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 256K ctx	2.3 GB	8.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Ministral3Model
Parameters: 1.1 B
Tensor type: BF16
Context length: 262,144
Vocabulary: 131,072
Layers / heads: 16 / 24
Licence: other
First seen on the Hub: 2026-07-14
Training datasets: undisclosed
Added to our catalog: 2026-08-03

Compare with

all-MiniLM-L6-v2 257.8 M paraphrase-multilingual-MiniLM-L12-v2 59.4 M bge-m3 35.0 M nomic-embed-text-v1 5.1 M all-MiniLM-L12-v2 3.5 M snowflake-arctic-embed-xs 2.5 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB