llama-3.3-70b Benchmarks

Provider: fireworks

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 fireworks provider hub to compare every tracked model side-by-side.

Visit fireworks Official Website

Benchmark Overview

Avg Tokens / Second

42.00

Avg Time to First Token (ms)

1240.00

Runs Analysed

237

Last Updated

Feb 8, 2026, 03:01 PM

Key Insights

  • llama-3.3-70b streams at 42.00 tokens/second on average across the last 237 benchmark runs.

  • Performance fluctuated by 71.41 tokens/second (170.0% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 1240.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.

  • Latest measurements completed on Feb 8, 2026, 03:01 PM based on 237 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)
fireworksllama-3.3-70b42.006.5978.001240.00

Frequently Asked Questions

The latest rolling average throughput is 42.00 tokens per second with an average time to first token of 1240.00 ms across 237 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 8, 2026, 03:01 PM.

Related Links