Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B is a sparse hybrid Mamba-Transformer mixture-of-experts (MoE) model with 30B total parameters but only 3B active per token. It supports a context window of 262.1K tokens with throughput closer to a 3B dense model than a 30B one.
Reasoning
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'nvidia/nemotron-3-nano-30b-a3b', prompt: 'Why is the sky blue?'})More models by NVIDIA
| Model |
|---|
| 1M | 2.3s | 225tps | $0.37/M | $1.08/M | Read:$0.12/M Write:— | — | — | +1 |    +1 | 06/04/2026 | |||
| 256K | 0.2s | 124tps | $0.15/M | $0.65/M | Read:— Write:$0.06/M | — | — |  | 03/18/2026 | ||||
| 131K | 0.2s | 154tps | $0.06/M | $0.23/M | — | — | | 08/18/2025 | |||||
| 131K | 0.2s | $0.20/M | $0.60/M | — | — | +1 | | 12/01/2024 |
