Compare AI models

Specifications
Parameters
16B8B
Context window
4k4k
Benchmarks
MMLU
47.2%54.4%
Overview
CompanyDeepSeekNVIDIA
Release dateJan 11 2024Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron-3 8B leads DeepSeek-MoE on 1 of the 1 benchmark they both report (MMLU). Nemotron-3 8B shipped 57 days before DeepSeek-MoE, so benchmark comparisons should account for the intervening progress.

DeepSeek-MoE has 16B parameters, while Nemotron-3 8B has 8B. Context windows are 4k (DeepSeek-MoE) vs 4k (Nemotron-3 8B).

On MMLU, Nemotron-3 8B leads at 54.4% vs DeepSeek-MoE at 47.2%.