llama-3-8b by deepinfra Benchmarks

Stale Data

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 The data shown may be outdated.

Last benchmark: March 8, 2026

Benchmark Overview

Avg Tokens / Second

45.50

Avg Time to First Token (ms)

310.00

Runs Analysed

239

Last Updated

Mar 8, 2026, 06:06 AM

llama-3-8b streams at 45.50 tokens/second on average across the last 239 benchmark runs.
Performance fluctuated by 60.98 tokens/second (134.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 310.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 8, 2026, 06:06 AM based on 239 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-3-8b	45.50	9.32	70.30	310.00

The latest rolling average throughput is 45.50 tokens per second with an average time to first token of 310.00 ms across 239 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 8, 2026, 06:06 AM.