Model Terminal

NVIDIA Nemotron Nano 9B V2 (free)

Nemotron Nano 9B V2 is NVIDIA's compact open-weight language model featuring a hybrid Mamba-2 and Transformer architecture designed for both instruction-following and extended chain-of-thought reasoning. It supports controllable 'thinking' behavior and is optimized for high inference throughput on long reasoning traces. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
NVIDIA
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed