Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightning- NVIDIA
- Family · Nemotron 3 Lightning
- Released 11 Aug 2026
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context1M
Max output236K
Input / 1M$0.07
Output / 1M$0.202.9× input
Scores · standing
Intelligence12.9#199/489
Coding26.8#117/196
Usage
Tokens / day148.9B▲ 3.8% 7d
Usage rank#28
Requests / day700.0K
Tool calls / req0.18
Per request · 30 days
Avg input5.2K0.3× median
Avg output7971.2× median
Cache hit55%0.8× median
Reasoning share75%1.3× median
Tool-call failures5.4%2.8× median
Consumption
Peak 18.4B 28 SepLow 1.5B 3 OctRank today #28
News & trends
2 mentions this week ▼ 33%this model · videos, posts, articles · 30 days
Trending · 14 days
- boro64/Ternary-Nemotron-3.5-Lightning-30B-A3B-GGUF · Hugging Face #Shorts1.1K views
- Qwen 3.7 vs Nemotron 3.5 Lightning (free): 784 vs 516 lines of Donkey Kong Country129 views
News · latest from NVIDIA
- Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKSAWS · 29 Oct
- NVIDIA Open Models Advance Europe’s Sovereign Intelligence Across IndustriesNVIDIA · 21 Oct
- NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal ReasoningNVIDIA · 15 Oct
- Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt ModelsNVIDIA · 15 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 6 providers, latest day
Output speed#98/33391 tok/s1.4× faster than median
Fastest provider254 tok/sbest of 6 providers
First token#270.35 s2.9× quicker than median
First answer token#387.57 sthinking included
#5 cheapest of 28 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Technical details
- Tokenizer
- Other
- License
- other
- Parameters
- 31.6B
- Moderation
- none
- Downloads · likes
- 1.2M · 258
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Low-cost bulk text processing
- Data analysis and design drafting
- Very long context summarization
- Fast tool-calling assistants
- Self-hosted high-throughput serving
Think twice for
- Hardest coding agents
- Browser automation agents
- Image understanding
Research papers
Social
Most watched and discussed · 90 days
- boro64/Ternary-Nemotron-3.5-Lightning-30B-A3B-GGUF · Hugging Face #ShortsMorningcoffeebyte · 1.1K views · 26 Oct
- Qwen 3.7 vs Nemotron 3.5 Lightning (free): 784 vs 516 lines of Donkey Kong CountryOpenLLMVS · 129 views · 21 Oct
- Nemotron 3.5 Lightning (free) vs Qwen 3.7: Qwen 3.7 is 1-1 here. Can it code NBA Jam?OpenLLMVS · 44 views · 21 Oct
- NVIDIA Nemotron 3.5 Lightning: 4x Faster AI Agents with 3B Active Parameters! 🚀Micro Learning · 7 views · 21 Oct
Alternatives
other vendors · similar capability- 8.5
- 10.0
- 13.0
- 13.3
Want Nemotron 3.5 Lightning on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.