llama-3.3-70b Benchmarks

Provider: deepinfra

Explore real-world latency and throughput results for llama-3.3-70b. 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

22.50

Avg Time to First Token (ms)

1060.00

Runs Analysed

231

Last Updated

Feb 16, 2026, 06:00 PM

Key Insights

  • llama-3.3-70b streams at 22.50 tokens/second on average across the last 231 benchmark runs.

  • Performance fluctuated by 56.95 tokens/second (253.1% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 1060.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.

  • Latest measurements completed on Feb 16, 2026, 06:00 PM based on 231 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-3.3-70b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
deepinfrallama-3.3-70b22.501.4558.401060.00

Frequently Asked Questions

The latest rolling average throughput is 22.50 tokens per second with an average time to first token of 1060.00 ms across 231 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 16, 2026, 06:00 PM.

Related Links