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 The data shown may be outdated.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: March 27, 2026

Benchmark Overview

Avg Tokens / Second

34.30

Avg Time to First Token (ms)

860.00

Runs Analysed

191

Last Updated

Mar 27, 2026, 06:00 PM

llama-3.2-90b streams at 34.30 tokens/second on average across the last 191 benchmark runs.
Performance fluctuated by 76.57 tokens/second (223.2% 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 Mar 27, 2026, 06:00 PM based on 191 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	34.30	4.73	81.30	860.00

The latest rolling average throughput is 34.30 tokens per second with an average time to first token of 860.00 ms across 191 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 27, 2026, 06:00 PM.