llama-3.1-70b by deepinfra Benchmarks

Stale Data

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 The data shown may be outdated.

Last benchmark: May 11, 2026

Benchmark Overview

Avg Tokens / Second

22.10

Avg Time to First Token (ms)

640.00

Runs Analysed

225

Last Updated

May 11, 2026, 10:48 AM

llama-3.1-70b streams at 22.10 tokens/second on average across the last 225 benchmark runs.
Performance fluctuated by 34.10 tokens/second (154.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 640.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 11, 2026, 10:48 AM based on 225 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-3.1-70b	22.10	5.30	39.40	640.00

The latest rolling average throughput is 22.10 tokens per second with an average time to first token of 640.00 ms across 225 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 11, 2026, 10:48 AM.