nvidia
NVIDIA: Nemotron 3.5 Lightning (free)
nvidia/nemotron-3.5-lightning:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
NVIDIA Nemotron 3.5 Lightning (free), listed on OpenRouter as nvidia/nemotron-3.5-lightning:free, is a text-in, text-out open mixture-of-experts model with 30B total and 3B active parameters in a hybrid Mamba-2, MoE, and attention architecture. The vendor card describes context support up to 1M tokens, toggleable reasoning, tool calling, and six supported languages. The published BF16 weights are positioned mainly for customization and post-training rather than direct production serving, for which NVIDIA recommends its quantized NVFP4 release.[1][2]
Strengths
- Vendor-reported context window up to 1M tokens, though validated single-GPU deployments reach 256K.[1][2]
- Reasoning mode configurable on or off, plus tool-calling support and configurable sampling parameters.[1][2]
- Hybrid MoE design activates 3B of 30B parameters per token, which NVIDIA positions for high-throughput agentic workloads.[1][2]
Limitations
- NVIDIA describes this BF16 release as a reference checkpoint for customization; for production inference it directs users to the quantized NVFP4 variant.[2]
- The full 1M-token context is validated only on multi-GPU or Blackwell setups; a single H100 is memory-bound to 256K.[2]
- Evidence is limited to the vendor card and a catalog listing; benchmark tables come from NVIDIA's own harness, so independent validation on your workload is still needed.[1][2]
Where to use it
- Fine-tuning, distillation, or domain adaptation for teams wanting full-precision open weights under the OpenMDW-1.1 license.[2]
- Prototyping agentic and tool-calling pipelines that can exploit the long context window.[1][2]
- Research and evaluation that require full-precision weights and reproducible benchmark recipes.[2]
Sources
- [1] OpenRouter catalog · NVIDIA: Nemotron 3.5 Lightning (free)Sources checked: Nov 13, 2026
- [2] Model documentation · NVIDIA: Nemotron 3.5 Lightning (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Specifications
- Model ID
- nvidia/nemotron-3.5-lightning:free
- Canonical ID
- nvidia/nemotron-3.5-lightning-20260807
- Creator
- nvidia
- Added to OpenRouter
- 11.08.2026
- Context length
- 1,000,000
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 5.5 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 26.8 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 3.5 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nvidianvfp4 | 1,000,000 | $0 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.