Not established from the available sources.
NVIDIA · MODEL RELEASE TRACKER
Nemotron-3.5 Lightning
Nemotron-3.5 Lightning is a text-only model from NVIDIA that the article demonstrates running on NVIDIA DGX Spark using TensorRT Edge-LLM and the trtedge CLI; it can be served locally with an OpenAI-compatible API server and targeted for edge deployment workflows.CURRENT SNAPSHOT2/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalityDescribed as a text-only model.
Not established from the available sources.
Runnable on DGX Spark with TensorRT Edge-LLMThe article demonstrates running Nemotron-3.5 Lightning on NVIDIA DGX Spark using TensorRT Edge-LLM and the trtedge CLI to download the model and build optimized TensorRT engines.
Local serving via OpenAI-compatible API serverAn OpenAI-compatible API server can serve the model locally for application prototyping and testing.
VERIFIABLE FACTS
Every value stays attached to a source and date.
MODALITIES · ModalityDEVELOPER CLAIM
Described as a text-only model.
AVAILABILITY · Runnable on DGX Spark with TensorRT Edge-LLMDEVELOPER CLAIM
The article demonstrates running Nemotron-3.5 Lightning on NVIDIA DGX Spark using TensorRT Edge-LLM and the trtedge CLI to download the model and build optimized TensorRT engines.
AVAILABILITY · Local serving via OpenAI-compatible API serverDEVELOPER CLAIM
An OpenAI-compatible API server can serve the model locally for application prototyping and testing.
CAPABILITIES · Supports interactive chat sessions via trtedge CLIDEVELOPER CLAIM
The trtedge CLI can download the model and build optimized TensorRT engines, enabling a chat session with Nemotron-3.5 Lightning in a few commands.
WHAT CHANGED