Nemotron 3.5 Lightning is NVIDIA's agent-focused open model, released on August 11, 2026 with 30 billion total parameters and roughly 3 billion active per token. The architecture interleaves Mamba-2 and Mixture-of-Experts layers with a small number of attention layers, which keeps throughput high and memory demand modest relative to the nominal parameter count. NVIDIA reports 86% on PinchBench and publishes the weights, training data and recipes under the permissive OpenMDW-1.1 license, which allows commercial use and modification with no licensing fee. The model targets high-frequency agent loops and tool calling, and NVIDIA lists deployment targets running from Jetson and the GeForce RTX 5090 through DGX Spark and DGX Station up to data centre and cloud hardware.
Nemotron-3_5-Lightning runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| EU | Not by default | No | $0.06 | $0.24 |
Nemotron-3_5-Lightning runs on a single route through the qynio gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting Nemotron-3_5-Lightning has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is not on by default — abuse monitoring. No training on customer data. EU; deposit available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Nemotron-3_5-Lightning through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "nebius/nvidia/Nemotron-3_5-Lightning",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
