Back to Models

Llama 3.1 Nemotron Ultra 253B v1

NVIDIA-tuned 253B Llama 3.1 model optimized for enterprise applications and instruction following

Parameters
253 B
Context
128,000 tokens
Released
Nov 1, 2024

Leaderboards

Performance vs. Industry Average

Intelligence

Llama 3.1 Nemotron Ultra 253B v1 is of lower intelligence compared to average (4.1), with an intelligence score of 4.0.

Price

Llama 3.1 Nemotron Ultra 253B v1 is cheaper compared to average ($0.91 per 1M Tokens) with a price of $0.35 per 1M Tokens.

Latency

Llama 3.1 Nemotron Ultra 253B v1 has a higher average latency compared to average (45.24s), with an average latency of 61.54s.

P99 Latency

Llama 3.1 Nemotron Ultra 253B v1 has a higher P99 latency compared to average (172.60s), taking 201.97s to receive the first token at P99 (TTFT).

Context Window

Llama 3.1 Nemotron Ultra 253B v1 has a smaller context window than average (246k tokens), with a context window of 128k tokens.

Llama 3.1 Nemotron Ultra 253B v1 - AutoBench