AI Hub
All models
LLMOpen weights

Llama 3.1 Nemotron 70B Instruct

NVIDIA

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type
LLM
Access
Open weights
Released
October 1, 2024
License
LLAMA 3 1 community license
Parameters
70000000000
Knowledge cutoff
December 1, 2023
Output speed
292 tok/s
Latency (TTFT)
0.24s
API pricing
$1.20 in · $1.20 out / 1M tokens

Benchmarks

Compare Llama 3.1 Nemotron 70B Instruct with

See all Llama 3.1 Nemotron 70B Instruct alternatives →