March 11, 2026
NVIDIA Nemotron 3 Super launches today! We've been building voice agents with Super's pre-release checkpoints and running all our various tests and benchmarks.
Nemotron 3 Super matches both GPT-5.4 and GPT-4.1 in tool calling and instruction following performance on our realtime conversation, long context, real-world benchmarks. GPT-4.1 is the most widely used LLM today for production voice agents. So an open model that performs as well as GPT-4.1 on hard, voice-specific benchmarks is a big deal.
(Side note: we don't think a benchmark "tells the story" about a model's voice agent performance unless it tests model correctness across at least 20 human/agent conversation turns.)
The Nemotron models are *fully* open: weights, data sets, training code, inference code.
Nemotron 3 Super is 120B params, with a hybrid Mamba-Transformer MoE architecture for efficient inference. You can run it on NVIDIA data center hardware or on a DGX Spark mini-desktop machine.
1M token context.
Blog post with full benchmarks, thinking budget notes, inference setup on @Modal, and where we think this goes next. 👇
Nemotron 3 Super for Voice Agents:
[1]
NVIDIA announcement post[2]
Open source benchmarks:
[3]
[4]
Also, a note about flexibility of this model: I've done a bunch of testing of the NVFP4 quant on my DGX Spark, and the results on my real-world benchmarks don't show any quality difference with the full BF16 weights. This is hard enough to believe that I'm going to keep poking at it! But suffice it to say that the NVFP4 version of this model is excellent.
Detailed notes on the model's architecture, training, and benchmarks here:
https://t.co/VQD02o4XBw