Nemotron 3.5 Lightning
StandardRun locallyNVIDIA's open 30B MoE built for high-throughput agentic workloads.
3B active parameters with a 256K-token context and toggleable reasoning. Also suited to specialized tasks that benefit from domain-specific customization. Runs locally through the Ollama daemon.
▼
Nemotron 3.5 Lightning is somewhat expensive at $0.08/M tokens input and $0.20/M tokens output. Cached input reads are priced at $0.04/M tokens, making repeated context cheaper. The model supports extended reasoning, a 262K context window.
Benchmarks
Specifications
Performance
Providers
Run locally
Run Nemotron 3.5 Lightning on your own computer with the Private AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.
ollama pull nemotron-3.5-lightning:30b
Misc
Compare with
GPT 6 Astravs Nemotron 3.5 LightningGPT 5.6 Lunavs Nemotron 3.5 Lightning
Claude Fable 5.1vs Nemotron 3.5 LightningClaude Opus 5vs Nemotron 3.5 LightningClaude Sonnet 5vs Nemotron 3.5 LightningClaude Haiku 4.5vs Nemotron 3.5 Lightning
Gemini 3.8 Flashvs Nemotron 3.5 LightningGemini 3.5 Flashvs Nemotron 3.5 LightningGemini 3.5 Flash-Litevs Nemotron 3.5 LightningGemma 4 31Bvs Nemotron 3.5 Lightning
Grok 4.6vs Nemotron 3.5 LightningGrok Build 0.1vs Nemotron 3.5 LightningGrok 4.1 Fastvs Nemotron 3.5 Lightning
Muse Spark 1.3vs Nemotron 3.5 Lightning
DeepSeek V4 Pro (0813)vs Nemotron 3.5 LightningDeepSeek V4 Flashvs Nemotron 3.5 Lightning
MiniMax M3vs Nemotron 3.5 Lightning
GLM 5.3vs Nemotron 3.5 LightningGLM 5.3 Flashvs Nemotron 3.5 Lightning
Qwen3.8 Max (0902)vs Nemotron 3.5 LightningQwen3.7 Plusvs Nemotron 3.5 LightningQwen3 Coder Nextvs Nemotron 3.5 Lightning
Nemotron 3 Ultravs Nemotron 3.5 LightningFrequently Asked Questions about Nemotron 3.5 Lightning▼
When was Nemotron 3.5 Lightning released?
▼
Nemotron 3.5 Lightning was released on August 11, 2026.
Who created Nemotron 3.5 Lightning?
▼
Nemotron 3.5 Lightning was created by NVIDIA.
How much does Nemotron 3.5 Lightning cost?
▼
Nemotron 3.5 Lightning costs $0.08/M input tokens and $0.20/M output tokens.
What is Nemotron 3.5 Lightning API pricing?
▼
The Nemotron 3.5 Lightning API is priced at $0.08 per million input tokens and $0.20 per million output tokens. You can access Nemotron 3.5 Lightning through idapt.app alongside 200+ other AI models in one workspace.
Is Nemotron 3.5 Lightning a reasoning model?
▼
Yes, Nemotron 3.5 Lightning is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.
Does Nemotron 3.5 Lightning support image or vision input?
▼
No, Nemotron 3.5 Lightning does not currently support image or vision input. It is a text-only model.
Does Nemotron 3.5 Lightning support audio?
▼
No, Nemotron 3.5 Lightning does not support audio input.
What is the context window of Nemotron 3.5 Lightning?
▼
Nemotron 3.5 Lightning has a context window of 262K tokens, meaning it can process approximately 196,608 words of context at once.
Is Nemotron 3.5 Lightning open source?
▼
Nemotron 3.5 Lightning is a proprietary model developed by NVIDIA. The model weights and training data are not publicly available.
Where can I use Nemotron 3.5 Lightning?
▼
You can chat with Nemotron 3.5 Lightning on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Nemotron 3.5 Lightning through NVIDIA's own API or platform.