Compare AI models

Specifications
Parameters
8B/70B/405B4B
Context window
128k256k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
49%53.2%
Overview
CompanyMetaNVIDIA
Release dateJul 23 2024Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Nano 4B leads LLaMA 3.1 on 1 of the 1 benchmark they both report (GPQA Diamond). LLaMA 3.1 shipped 601 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 128k (LLaMA 3.1) vs 256k (Nemotron 3 Nano 4B).

On GPQA Diamond, Nemotron 3 Nano 4B leads at 53.2% vs LLaMA 3.1 at 49%.