HF model

nvidia / NVIDIA-Nemotron-Nano-9B-v2-Japanese

A 9‑billion‑parameter Japanese‑optimized LLM, NVIDIA Nemotron‑Nano‑9B‑v2‑Japanese, trained on data up to September 2024 with a hybrid Mamba‑2/MLP/4‑layer‑attention architecture, fine‑tuned on the Nemotron‑Personas‑Japan tool‑calling dataset, that optionally generates a controllable reasoning trace before producing a final answer and is available for commercial use.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
3,000
Hugging Face likes
146
Listed
Feb 24, 2026

Downloads (30-day window) over time

0200k400k600kNovSepJulMayMarJan 20263,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 20269,000
Mar 2026568,000
Apr 2026194,000
May 2026155,000
Jun 2026108,000
Jul 20264,000
Aug 20264,000
Sep 20263,000
Oct 20263,000
Nov 20263,000

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category

Resources in similar research fields

Learn from slides & articles