llama-3.3-70b Benchmarks

Provider: cerebras

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

Visit cerebras Official Website

Benchmark Overview

Avg Tokens / Second

216.00

Avg Time to First Token (ms)

370.00

Runs Analysed

234

Last Updated

Feb 8, 2026, 09:00 PM

Key Insights

  • llama-3.3-70b streams at 216.00 tokens/second on average across the last 234 benchmark runs.

  • Performance fluctuated by 323.40 tokens/second (149.7% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 370.00 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Feb 8, 2026, 09:00 PM based on 234 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)
cerebrasllama-3.3-70b216.0014.60338.00370.00

Frequently Asked Questions

The latest rolling average throughput is 216.00 tokens per second with an average time to first token of 370.00 ms across 234 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 8, 2026, 09:00 PM.

Related Links