NVIDIA Nemotron 3.5 Lightning 30B A3B

NVIDIA hybrid Mamba-Transformer MoE (30B params, 3B active) with a multi-token prediction head, for low-latency agentic serving at long context.

262K context·$0.05 in·$0.20 out·Aug 2026 release·Reasoning, Tools / functions

Available on

Fireworks AI

Providers

Where NVIDIA Nemotron 3.5 Lightning 30B A3B runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutputCache read

Fireworks AI

accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b

262K

$0.05

$0.20

$0.01

Specs as reported by each service · usage over the last 2 days · refreshed hourly

Run NVIDIA Nemotron 3.5 Lightning 30B A3B in Big-AGI.

Connect your own key on any of the services above, at their rates, no markup - and run it side by side with every other model.

Launch Big-AGI

BIG-AGI

Product

Features Models Controls What's new BEAM Technology

Resources

Documentation Discord GitHub

Company

Email Us Privacy Terms