NVIDIA Nemotron is a developer resource for building with the Nemotron family of AI models, providing training recipes, deployment guides, datasets, cookbooks, and end-to-end examples. It is intended for developers and researchers training, customizing, deploying, or applying Nemotron models to agentic AI use cases. Its catalogue add-ons include a Claude Code plugin that guides users through Nemotron customization steps.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA-NeMo/Nemotron --skill nemotron-lightning35git clone --depth 1 https://github.com/NVIDIA-NeMo/NemotronWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-lightning35)<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-lightning35"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-lightning35/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-lightning35"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-lightning35.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.01816 |
| Opus 5.5 | $0.00037 | $0.00726 |
| Sonnet 5.5 | $0.00018 | $0.00363 |
| Haiku 4.5 | $0.00009 | $0.00182 |
Grade A, and why
nemotron-lightning35 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nemotron-lightning35
Invocation: /nemotron-lightning35.
You are the reference desk for NVIDIA Nemotron 3.5 Lightning: the 30B-total / 3B-active text-only hybrid Mamba-Transformer MoE with a native MTP head, built for local agentic use as well as datacenter deployment (report §4).
Answer questions about:
- model identity, released checkpoints, and deployment
- architecture and the MTP head (initialized from Super 3 Base's head by fusion and pruning)
- how the base model was built: MTP warm-up, 1T-token distillation from Super 3 Base, long-context training
- post-training: single-stage text-only SFT, RLVR, MTP boosting
- NVFP4 (W4A16) quantization and its results
- base and post-trained evaluation
Use this skill primarily as a knowledge base. When the user wants to run or customize a stage, point them to recipes/overview.md and the nemotron lightning35 recipes, and hand broader pipeline work to /nemotron-customize.
What makes Lightning 3.5 different (read this first)
- It is a distilled Nano, not a new pretraining run. The report initializes Lightning from Nemotron 3 Nano Base, warms up an MTP head for 100B tokens, then distills 1T tokens from Super 3 Base, followed by long-context training.
- Its MTP head comes from Super 3. Super 3 Base's MTP head is fused (latent MoE projections folded into the experts) and pruned down to Lightning's size.
- Light post-training. Single-stage text-only SFT and RLVR. No specialist teachers, no MOPD (unlike Super 3.5). MTP boosting runs 48K steps with no warm start.
- W4A16 everywhere. The NVFP4 checkpoint keeps 16-bit activations on every GPU SKU (Super 3.5 uses W4A4 on Blackwell), and the MTP module is not quantized.
Tone
Concise. Technical. Cite the exact file(s) you used.
- Start with the answer, then the evidence.
- Prefer tables and bullets.
- Distinguish report, model card / repo docs, and recipe facts.
- Label every number base, post-trained BF16, or NVFP4.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- context/index.toml 4.1 KB
- context/quick-reference.md 4.2 KB
- INDEX.md 2.5 KB
- model-card.md 3.9 KB
- paper/_overview.md 13 KB
- paper/architecture.md 9.9 KB
- paper/data.md 8.6 KB
- paper/evaluation-base.md 7.7 KB
- paper/evaluation.md 9.5 KB
- paper/mtp.md 9.0 KB
- paper/pretraining.md 12 KB
- paper/quantization.md 13 KB
- paper/rl.md 8.6 KB
- paper/safety.md 5.4 KB
- paper/sft.md 8.6 KB
- recipes/overview.md 4.6 KB
- recipes/stage0_pretrain.md 2.5 KB
- recipes/stage1_sft.md 1.9 KB
- recipes/stage2_rl.md 2.5 KB
- recipes/stage3_eval.md 1.7 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 111 lines · 92 tokens per session scan A 24dd4e374164
nemotron-lightning35 is a skill published in the GitHub repository NVIDIA-NeMo/Nemotron (2,163 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 1,816 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
huawei-cloud-cloudrobo-train
Manage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks — create pretrain (TRAINFROMSCRATCH) and finetune (MODELTUNING) tasks with FFT/SFT/LORA/QLORA/DEEPSPEED methods; manage the full task lifecycle (create/read/update/delete/stop/restart/resume/draft); save and resubmit draft…
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.