Modelofficial release

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Nemotron →Hugging Face ↗
Parameters31.6B (3B active)
Context256K
Input → outputtext → text
Licenseother
PrecisionBF16
ArchitectureNemotronHForCausalLM
ReleasedAug 1, 2026
Downloads615.1K

Other sizes and formats in the family

ModelParamsPrecisionDownloads
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF1631.6BBF1632.9K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4nvfp417.8BU8828.9K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSparknvfp4764MBF16132.2K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlashnvfp4663MBF161.4K

Compare side by side →

Built on this model

ModelParamsPrecisionDownloads
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSparknvfp4764MBF16132.2K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlashnvfp4663MBF161.4K

This release in the news

No coverage of this exact release yet.

Recent news about Nemotron

  1. Oct 12, 2026 · Open-source release
    unslothai/unsloth v0.1.906-beta: Browser Use + Qwen-Image-2.1-Turbo
  2. Oct 8, 2026 · Product / feature launch
    Microsoft Joins the Local AI Push
  3. Oct 7, 2026 · Benchmark result
    One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
  4. Oct 7, 2026 · Model release
    [AINews] Reflection Beam - 501B-A23B American Open Model
  5. Oct 6, 2026 · Research paper
    Enhancing Diffusion Language Models with Autoregressive Post-Training Weights
  6. Oct 5, 2026 · Research paper
    SoloQ: Calibration-Free Quantization for Diffusion Language Models
  7. Oct 2, 2026 · Open-source release
    sgl-project/sglang v0.5.21
  8. Oct 1, 2026 · Tutorial / explainer
    Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages