Nemotron 3.5 Lightning
Fast & cheapOpen weightsText30B total / 3B active (MoE)
A high-throughput NVIDIA MoE with free-first resilient routing.
This model competes in the arena. See where it ranks.
About the Nemotron family
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model with 30B total parameters and only 3B active per token. StudyArena sends its OpenRouter traffic to the free endpoint first, then automatically falls back to the paid CoreWeave route if the primary errors, is rate-limited or is down.
All Nemotron modelsHow this one is configured
The free primary supports a 1M-token text context and optional reasoning; direct-answer and reasoning modes are separate contestants. The paid fallback supports 262K tokens.
Who makes it
NVIDIA, United States. Not listed as a provider in this directory.
More from Nemotron
- Llama 3.1 Nemotron Instruct 70B
- Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)
- Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
- Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)
- Llama 3.3 Nemotron Super 49B v1 (Reasoning)
- Llama Nemotron Super 49B v1.5 (Non-reasoning)
- Llama Nemotron Super 49B v1.5 (Reasoning)
- Nemotron 3 Nano Omni 30B A3B Reasoning
- Nemotron 3 Ultra 550B A55B (Reasoning)
- Nemotron Cascade 2 30B A3B
- NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
- NVIDIA Nemotron 3 Nano 4B
- NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
- NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
- NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
- NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
- NVIDIA Nemotron Nano 9B V2 (Reasoning)