Compare AI models

Specifications
Parameters
8B/70B/405B8B/43B
Context window
128k4k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
These models have no shared benchmark scores.
Overview
CompanyMetaNVIDIA
Release dateJul 23 2024Mar 21 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

LLaMA 3.1 and NeMo GPT (8B/43B) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. NeMo GPT (8B/43B) shipped 490 days before LLaMA 3.1, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while NeMo GPT (8B/43B) has 8B/43B. Context windows are 128k (LLaMA 3.1) vs 4k (NeMo GPT (8B/43B)). LLaMA 3.1 is open weight, while NeMo GPT (8B/43B) is closed.

Direct benchmark comparisons are unavailable — LLaMA 3.1 and NeMo GPT (8B/43B) don't publish scores on any of the same benchmarks.