llama-3.2-90b by deepinfra Benchmarks

Stale Data

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 The data shown may be outdated.

Last benchmark: May 11, 2026

Benchmark Overview

Avg Tokens / Second

25.70

Avg Time to First Token (ms)

470.00

Runs Analysed

215

Last Updated

May 11, 2026, 03:33 PM

llama-3.2-90b streams at 25.70 tokens/second on average across the last 215 benchmark runs.
Performance fluctuated by 26.80 tokens/second (104.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 470.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 11, 2026, 03:33 PM based on 215 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-3.2-90b	25.70	14.90	41.70	470.00

The latest rolling average throughput is 25.70 tokens per second with an average time to first token of 470.00 ms across 215 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 11, 2026, 03:33 PM.