NVIDIA
NVIDIA
Embedding model · United States ·Feb 2026

Llama-NV-Embed-Reasoning-3B

Embedding Open (Restricted)
3.2B
Parameters
8.2K
Context

About Llama-NV-Embed-Reasoning-3B

Llama-NV-Embed-Reasoning-3B is an AI model developed by NVIDIA, in the embedding category, released in 2026, made available as an open-weights model with 3.2B params. A 3.2B-parameter decoder-based text embedding model built on Llama-3.2-3B, producing up to 3072-dim embeddings and speci.

On this page you'll find Llama-NV-Embed-Reasoning-3B's full specifications, including a context window of 8.2K tokens. Review provider pricing and benchmark scores below, or compare Llama-NV-Embed-Reasoning-3B head-to-head with other embedding models.

→ More models by NVIDIA → All embedding models → AI benchmarks leaderboard

Community

Would you run Llama-NV-Embed-Reasoning-3B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Llama-NV-Embed-Reasoning-3B

NVIDIA
NVIDIA Nemotron 3 Ultra
NVIDIA · 550B
 NVIDIA
NVIDIA Nemotron 3.5 ASR Streaming 0.6B
NVIDIA · 600M
 NVIDIA
NVIDIA Nemotron 3.5 Content Safety
NVIDIA · 4B
 NVIDIA
NVIDIA Cosmos 3
NVIDIA · 64B
 NVIDIA
NVIDIA Nemotron 3 Nano Omni
NVIDIA · 31.6B
 NVIDIA
Nemotron 3 Super
NVIDIA

Frequently asked questions

What is Llama-NV-Embed-Reasoning-3B? ▶

A 3.2B-parameter decoder-based text embedding model built on Llama-3.2-3B, producing up to 3072-dim embeddings and speci It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Llama-NV-Embed-Reasoning-3B? ▶

Llama-NV-Embed-Reasoning-3B was developed by NVIDIA and released in 2026.

Is Llama-NV-Embed-Reasoning-3B open source or proprietary? ▶

Llama-NV-Embed-Reasoning-3B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

What is Llama-NV-Embed-Reasoning-3B's context window? ▶

Llama-NV-Embed-Reasoning-3B supports a context window of 8.2K tokens, and has 3.2B params.

How much does Llama-NV-Embed-Reasoning-3B cost? ▶

Pricing for Llama-NV-Embed-Reasoning-3B depends on the provider. See the providers table on this page for the latest API rates.

How does Llama-NV-Embed-Reasoning-3B perform on benchmarks? ▶

Benchmark scores for Llama-NV-Embed-Reasoning-3B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about Llama-NV-Embed-Reasoning-3B?