API Status

llama-3-8b Benchmarks

Provider: deepinfra

Explore real-world latency and throughput results for llama-3-8b. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the deepinfra provider hub to compare every tracked model side-by-side.

Visit deepinfra Official Website

Benchmark Overview

Avg Tokens / Second

44.90

Avg Time to First Token (ms)

330.00

Runs Analysed

240

Last Updated

Mar 27, 2026, 12:01 AM

Key Insights

  • llama-3-8b streams at 44.90 tokens/second on average across the last 240 benchmark runs.

  • Performance fluctuated by 49.90 tokens/second (111.1% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 330.00 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Mar 27, 2026, 12:01 AM based on 240 total samples.

Performance Distribution

Distribution of throughput measurements showing performance consistency across benchmark runs.

Performance Over Time

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

llama-3-8b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
deepinfrallama-3-8b44.9018.8068.70330.00

Frequently Asked Questions

The latest rolling average throughput is 44.90 tokens per second with an average time to first token of 330.00 ms across 240 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 27, 2026, 12:01 AM.

Related Links