llama-3.2-3b by deepinfra Benchmarks

Stale Data

This model has not returned successful benchmark results recently. The data shown may be outdated.

Last benchmark: February 8, 2026

Benchmark Overview

Avg Tokens / Second

26.80

Avg Time to First Token (ms)

640.00

Runs Analysed

233

Last Updated

Feb 8, 2026, 12:00 PM

llama-3.2-3b streams at 26.80 tokens/second on average across the last 233 benchmark runs.
Performance fluctuated by 88.17 tokens/second (329.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 640.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 8, 2026, 12:00 PM based on 233 total samples.

Distribution of throughput measurements showing performance consistency across benchmark runs.

Historical performance trends showing how throughput has changed over the benchmarking period.

Provider	Model	Avg Toks/Sec	Min	Max	Avg TTF (ms)
deepinfra	llama-3.2-3b	26.80	1.03	89.20	640.00

The latest rolling average throughput is 26.80 tokens per second with an average time to first token of 640.00 ms across 233 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 8, 2026, 12:00 PM.