Compare AI models

Specifications
Parameters
51B14.3B
Context window
128k32k
Benchmarks
MMLU
80.2%62.5%
GSM8K
91.43%61.5%
Overview
CompanyNVIDIAQwen
Release dateSep 23 2024Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 51B leads Qwen1.5-MoE on 2 of the 2 benchmarks they both report (MMLU, GSM8K). Qwen1.5-MoE shipped 179 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

Llama 3.1 Nemotron 51B has 51B parameters, while Qwen1.5-MoE has 14.3B. Context windows are 128k (Llama 3.1 Nemotron 51B) vs 32k (Qwen1.5-MoE).

On MMLU, Llama 3.1 Nemotron 51B leads at 80.2% vs Qwen1.5-MoE at 62.5%. On GSM8K, Llama 3.1 Nemotron 51B leads at 91.43% vs Qwen1.5-MoE at 61.5%.