AION
Modelofficial release

nvidia/Nemotron-3-Labs-Ultra-Math-SFT

Parameters561B
Context256K
Input → outputtext → text
Licenseother
PrecisionBF16
ArchitectureNemotronHForCausalLM
ReleasedSep 2, 2026
Downloads2.4K

Based on nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Other sizes and formats in the family

ModelParamsPrecisionDownloads
nvidia/Nemotron-3-Labs-Ultra-Math-RL561BBF161.3K

Compare side by side →

This release in the news

No coverage of this exact release yet.

Recent news about Nemotron

  1. Oct 7, 2026 · Opinion / analysis
    One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
  2. Oct 6, 2026 · Research paper
    Enhancing Diffusion Language Models with Autoregressive Post-Training Weights
  3. Oct 2, 2026 · Open-source release
    sgl-project/sglang v0.5.21
  4. Oct 1, 2026 · Tutorial / explainer
    Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages
  5. Sep 30, 2026 · Open-source release
    huggingface/transformers v5.18.0: Release 5.18.0
  6. Sep 29, 2026 · Open-source release
    NVIDIA/TensorRT-LLM v1.3.0rc29
  7. Sep 19, 2026 · Open-source release
    ollama/ollama v0.34.3
  8. Aug 22, 2026 · Open-source release
    sgl-project/sglang v0.5.18