The Information Machine
Concluded·following since 11 Aug 2026·Day 2·8 sources·updated 16 Aug 2026

NVIDIA Nemotron 3.5 Lightning and Switchyard

The gist

NVIDIA's Nemotron 3.5 Lightning and NeMo Switchyard draw external reviews showing speed gains alongside notable limits.

The external benchmarks give developers a clearer picture than NVIDIA's own figures: the model delivers strong inference speed but falls short on long-context comprehension, and the routing library shows real cost reductions in partner deployments while carrying acknowledged maturity gaps in version 0.2.

The full picture

NVIDIA released Nemotron 3.5 Lightning, a 30-billion-parameter mixture-of-experts model with 3 billion active parameters at inference time and a 1 million token context window, alongside NeMo Switchyard, an open-source model routing library, on August 11, 2026. External evaluations published since the launch have added both supporting data and qualifications to NVIDIA's claims.

On Nemotron 3.5 Lightning: Artificial Analysis rated it at 24 on their Intelligence Index, above the median of 9 for comparable open-weight models, and measured output speed at 296.7 tokens per second against a median of 101.6 t/s for the class. However, a review found that the model's 1 million token context window does not produce best-in-class long-context comprehension: on NVIDIA's own long-context benchmark, it scored 52.0, behind Qwen3.6 35B (61.06) and Gemma 4 26B (57.56). Competitive analysis places Lightning behind open models Qwen3.6 35B A3B and Muse Glimmer and behind closed models such as Gemini 3.6 Flash on general agent and coding evaluations, though the model showed major benchmark gains over its predecessor Nemotron 3 Nano.

On NeMo Switchyard: a detailed Cognition case study showed the router operating between Opus 5 and Kimi K2.7 on a production coding benchmark, achieving 50.6% accuracy at a $3.11 mean cost, which Cognition reported as approximately 28% lower than using Opus 5 alone. A separate review of version 0.2 concluded the library is not ready as a drop-in production dependency, citing documented gaps including upstream work continuing after client disconnect, undercounted retry recovery, and missing version headers.

How it developed
16 August 2026

Third-party evaluations published August 15 found Nemotron 3.5 Lightning, an NVIDIA mixture-of-experts model released August 11, at 296.7 tokens per second and an Artificial Analysis Intelligence Index of 24, both above open-weight medians, but trailing Qwen3.6 35B and Gemma 4 26B on NVIDIA's long-context benchmark.

A Cognition case study showed NeMo Switchyard, NVIDIA's routing library, cutting mean cost 28% between Opus 5 and Kimi K2.7, while a Wavect review concluded version 0.2 is not production-ready due to documented gaps.

11 August 2026

NVIDIA released Nemotron 3.5 Lightning and NeMo Switchyard via blog announcements.

Sources
3 more sources
The daily email

Want this in your inbox?

I send a short email each morning with the stories that moved. If you would rather just read here, that works too.

Subscribe free