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 The data shown may be outdated.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: February 8, 2026

Benchmark Overview

Avg Tokens / Second

38.30

Avg Time to First Token (ms)

860.00

Runs Analysed

199

Last Updated

Feb 8, 2026, 12:00 PM

llama-3.2-90b streams at 38.30 tokens/second on average across the last 199 benchmark runs.
Performance fluctuated by 90.93 tokens/second (237.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 860.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 8, 2026, 12:00 PM based on 199 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	38.30	1.77	92.70	860.00

The latest rolling average throughput is 38.30 tokens per second with an average time to first token of 860.00 ms across 199 recent runs.

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