Nemotron 3.5 Embed 8B

An estimated 6.1 GB at Q4, 10.3 GB at Q8 and 18.9 GB at FP16. These figures are estimates from the 8B parameter count, covering weights plus about 15% and 0.5 GB for a short context.

Yes, on all four. A 24 GB GPU fits at FP16 (estimated 18.9 GB), 16 GB and 12 GB GPUs fit at Q8 (estimated 10.3 GB) and an 8 GB GPU fits at Q4 (estimated 6.1 GB).

Yes, Q4 needs an estimated 6.1 GB. Assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits Q4 is 16 GB.

Yes. Nemotron 3.5 Embed 8B has open weights, so you can self-host it for full control of your data.

Run Nemotron 3.5 Embed 8B locally

The context window is 33K tokens (32,768) and the maximum output is 29K tokens (29,491).

Closest alternatives, matched on model kind and release date, are LFM2.5-Embedding-350M by Liquid AI, Titan Text Embeddings V2 by Amazon (blended price $0.015 per 1M tokens) and Titan Embeddings G1 - Text by Amazon (blended price $0.075 per 1M tokens).

LFM2.5-Embedding-350MNemotron 3.5 Embed 8B vs LFM2.5-Embedding-350MTitan Text Embeddings V2Nemotron 3.5 Embed 8B vs Titan Text Embeddings V2Titan Embeddings G1 - TextNemotron 3.5 Embed 8B vs Titan Embeddings G1 - Text

Nemotron 3.5 Embed 8B has a 33K token (32,768) context, costs $0.00 input and $0.00 output per 1M tokens and was released October 21, 2026. Nemotron 3.5 ASR Streaming Multilingual 0.6B costs $3.33 input and $0.00 output per 1M tokens and was released August 13, 2026.

Nemotron 3.5 ASR Streaming Multilingual 0.6BNemotron 3.5 Embed 8B vs Nemotron 3.5 ASR Streaming Multilingual 0.6B

Nemotron 3.5 Embed 8B has open weights.

The weights are available on Hugging Face in the repository nvidia/Nemotron-3.5-Embed-8B-BF16.

Run Nemotron 3.5 Embed 8B locally

NVIDIA made Nemotron 3.5 Embed 8B. It was first listed on OpenRouter on October 21, 2026.

More from NVIDIA

Yes, the model has open weights, so you can download and run it yourself.