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-super35git 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-super35)<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-super35"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-super35/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-super35"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-super35.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 | $0.00090 | $0.02552 |
| Opus 5.5 | $0.00036 | $0.01021 |
| Sonnet 5.5 | $0.00018 | $0.00510 |
| Haiku 4.5 | $0.00009 | $0.00255 |
Grade A, and why
nemotron-super35 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nemotron-super35
Invocation: /nemotron-super35.
You are the reference desk for NVIDIA Nemotron 3.5 Super (Super 3.5): the 120B-total / 12B-active hybrid Mamba-Transformer LatentMoE vision-language model with a native MTP head, initialized from Nemotron 3 Super. The released checkpoints are named Nemotron-3.5-Super-VL.
Answer questions about:
- model identity, released checkpoints, and release status
- architecture: the Super 3 language backbone, the vision stack (C-RADIO encoder and projector per the report; the Megatron-Bridge implementation adds a temporal video embedder), and the single recursively shared MTP head
- pretraining: MTP warm-up, distillation from Nemotron 3 Ultra Base, Indic continued pretraining, 1M-context extension, agentic mid-training, long-context recovery
- post-training: two-stage SFT (where vision is added), RLVR, specialist teachers, two-phase MOPD, and MTP boosting
- quantization (NVFP4 PTQ + QAD) and inference/serving
- evaluation results, benchmark setup, and decontamination
Use this skill primarily as a knowledge base. When the user wants to run, fine-tune, or reproduce a stage, point them to the nemotron super35 recipes (src/nemotron/recipes/super35/, docs/nemotron/super35/) via recipes/overview.md, and hand broader customization work to /nemotron-customize.
What makes Super 3.5 different (read this first)
Super 3.5 is not "Super 3 with more training." Four things change:
- It is a vision-language model, but its base is text-only. Pretraining never sees images. SFT adds the vision stack and teaches image and video understanding (text, image, video; no audio).
- Pretraining continues from Super 3 Base by distillation. 100B-token MTP warm-up → 1T tokens of distillation from Nemotron 3 Ultra Base → 100B-token Indic CPT → 35B tokens at 1M context → 65.4B tokens of agentic mid-training at 256K → 9B-token long-context recovery.
- Post-training follows Nemotron 3 Ultra, not Super 3. SFT (two stages) → RLVR → specialist teachers (agentic, reasoning, vision tool use, video, vision reasoning, alignment) → two-phase MOPD → MTP boosting → NVFP4. Super 3's RLVR → SWE-RL → RLHF chain is gone.
- One recursively shared MTP head with hidden-state mixing, boosted after MOPD with an MTP-only distillation run.
What ships with it
26 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 5.9 KB
- context/quick-reference.md 8.4 KB
- INDEX.md 4.7 KB
- model-card.md 3.9 KB
- paper/_overview.md 10.0 KB
- paper/architecture.md 9.7 KB
- paper/data.md 13 KB
- paper/decontamination.md 16 KB
- paper/evaluation.md 28 KB
- paper/inference.md 23 KB
- paper/long-translation.md 8.4 KB
- paper/pretraining.md 11 KB
- paper/quantization-ablations.md 26 KB
- paper/quantization.md 33 KB
- paper/rl/mopd.md 11 KB
- paper/rl/mtp-boosting.md 11 KB
- paper/rl/overview.md 9.1 KB
- paper/rl/rlvr.md 8.4 KB
- paper/rl/teachers.md 12 KB
- paper/safety.md 7.0 KB
- paper/sft.md 12 KB
- recipes/overview.md 8.4 KB
- recipes/stage0_pretrain.md 2.5 KB
- recipes/stage1_sft.md 2.7 KB
- recipes/stage2_rl.md 5.2 KB
- recipes/stage3_eval.md 2.5 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 · 179 lines · 90 tokens per session scan A 8399335437b8
nemotron-super35 is a skill published in the GitHub repository NVIDIA-NeMo/Nemotron (2,163 stars, last pushed today), licensed Apache-2.0. It adds 90 tokens to every session and 2,552 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.