llama-3-70b by deepinfra Benchmarks

Stale Data

This model has not returned successful benchmark results recently. The data shown may be outdated.

Last benchmark: June 10, 2026

Benchmark Overview

Avg Tokens / Second

29.30

Avg Time to First Token (ms)

0.00

Runs Analysed

Last Updated

Jun 10, 2026, 08:58 PM

llama-3-70b streams at 29.30 tokens/second on average across the last 81 benchmark runs.
Performance fluctuated by 34.27 tokens/second (117.0% coefficient of variation), indicating variable behavior across benchmark runs.
Latest measurements completed on Jun 10, 2026, 08:58 PM based on 81 total samples.

Distribution of throughput measurements showing performance consistency across benchmark runs.

Historical performance trends showing how throughput has changed over the benchmarking period.

Provider	Model	Avg Toks/Sec	Min	Max	Avg TTF (ms)
deepinfra	llama-3-70b	29.30	3.03	37.30	0.00

The latest rolling average throughput is 29.30 tokens per second with an average time to first token of 0.00 ms across 81 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 10, 2026, 08:58 PM.