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

35.50

Avg Time to First Token (ms)

330.00

Runs Analysed

3

Last Updated

Jan 2, 2026, 03:03 AM

Key Insights

  • llama-3.3-70b streams at 35.50 tokens/second on average across the last 3 benchmark runs.

  • Performance fluctuated by 15.40 tokens/second (43.4% 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 Jan 2, 2026, 03:03 AM based on 3 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-3.3-70b35.5027.2042.60330.00

Frequently Asked Questions

The latest rolling average throughput is 35.50 tokens per second with an average time to first token of 330.00 ms across 3 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jan 2, 2026, 03:03 AM.

Related Links