llama-3.1-70b Benchmarks

Provider: bedrock

Explore real-world latency and throughput results for llama-3.1-70b. 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 bedrock provider hub to compare every tracked model side-by-side.


Benchmark Overview

Avg Tokens / Second

25.10

Avg Time to First Token (ms)

0.56

Runs Analysed

1145

Last Updated

Dec 25, 2025, 05:07 PM

Key Insights

  • llama-3.1-70b streams at 25.10 tokens/second on average across the last 1145 benchmark runs.

  • Performance fluctuated by 13.40 tokens/second (53.4% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 0.56 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Dec 25, 2025, 05:07 PM based on 1145 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-3.1-70b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
bedrockllama-3.1-70b25.1012.8026.200.56

Frequently Asked Questions

The latest rolling average throughput is 25.10 tokens per second with an average time to first token of 0.56 ms across 1145 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Dec 25, 2025, 05:07 PM.

Related Links