← All models

Llama 3.1 Nemotron Nano 8B V1

NVIDIA · 2025-03-18 · 8B parameters

Llama 3.1 Nemotron Nano 8B V1 is NVIDIA's open-weight 8B reasoning model post-trained from Meta's Llama 3.1 8B Instruct and released on March 18, 2025; the released BF16 checkpoint contains exactly 8,030,261,248 parameters. It keeps the dense Llama 3.1 8B architecture and was post-trained with supervised fine-tuning for math, code, reasoning and tool calling followed by RLOO and online RPO stages, so reasoning can be switched on or off through the system prompt. It supports a 131,072-token context window and is the LN-Nano model of NVIDIA's Llama-Nemotron technical report.

Benchmark scores