Model Detail
Nemotron-Cascade-2-30B-A3B
—Nemotron-Cascade-2-30B-A3B is a code generation model with 30B parameters released by NVIDIA. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under a other license.
Nemotron-Cascade-2-30B-A3B ships with 30B parameters. Total weight footprint is approximately 31.6 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.
Nemotron-Cascade-2-30B-A3B is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
In-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B
arXiv:2610.15373v1 Announce Type: cross Abstract: We adapted Nemotron-3-Nano-30B-A3B for eight Indian languages without changing its backbone architecture. We expanded the vocabulary in place from 131,072 to 163,072 entries using continued byte-pair encoding and AdaptMix rebalancing, reducing tokens
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
arXiv:2609.10712v1 Announce Type: new Abstract: We study how model post-training and test-time inference design affect natural-language proof generation for hard olympiad mathematics. Starting from Nemotron 3 Ultra, we train two specialist checkpoints using supervised fine-tuning and reinforcement l
From a Multilingual Streaming ASR Backbone to Kenyan-Language Systems: Data-Centric Adaptation of Nemotron 3.5 for Kikuyu, Dholuo, and Kalenjin
arXiv:2607.18912v1 Announce Type: new Abstract: Automatic speech recognition (ASR) for African languages is constrained by orthographic inconsistency, annotation artifacts, missing audio, speaker and domain imbalance, and evaluation procedures that differ from deployment. We present an end-to-end en
