Compare AI models

Specifications
Parameters
30B4B
Context window
128k256k
API pricing
Cheapest input
$0.30DeepInfra—
Cheapest output
$1.20DeepInfra—
$120ModelRun · bf16—
Benchmarks
GPQA Diamond
83.5%53.2%
Overview
CompanyMetaNVIDIA
Release dateAug 10 2026Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Muse Glimmer leads Nemotron 3 Nano 4B on 1 of the 1 benchmark they both report (GPQA Diamond). Nemotron 3 Nano 4B shipped 147 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.

Muse Glimmer has 30B parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 128k (Muse Glimmer) vs 256k (Nemotron 3 Nano 4B).

On GPQA Diamond, Muse Glimmer leads at 83.5% vs Nemotron 3 Nano 4B at 53.2%.