Loading
Loading
How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5 Lightning illustrates the...
NVIDIA published a model update. If you use a hosted chat, read the source before you assume your usual model changed.
Try Nemotron 3.5 Lightning. Copy the OpenRouter call.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3.5-lightning","messages":[{"role":"user","content":"Hello"}]}'Published 2026-10-01T18:31:29.000Z. FitStack shortens the story so you can decide. The source owns the detail.