llama-3.1-8b by deepinfra Benchmarks

Stale Data

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 The data shown may be outdated.

Last benchmark: March 27, 2026

Benchmark Overview

Avg Tokens / Second

40.00

Avg Time to First Token (ms)

780.00

Runs Analysed

240

Last Updated

Mar 27, 2026, 03:03 PM

llama-3.1-8b streams at 40.00 tokens/second on average across the last 240 benchmark runs.
Performance fluctuated by 75.58 tokens/second (188.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 780.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 27, 2026, 03:03 PM based on 240 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-3.1-8b	40.00	2.42	78.00	780.00

The latest rolling average throughput is 40.00 tokens per second with an average time to first token of 780.00 ms across 240 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 27, 2026, 03:03 PM.