API Status

qwen-3.5-122b-a10b Benchmarks

Provider: deepinfra

Explore real-world latency and throughput results for qwen-3.5-122b-a10b. 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 deepinfra provider hub to compare every tracked model side-by-side.

Visit deepinfra Official Website

Benchmark Overview

Avg Tokens / Second

79.60

Avg Time to First Token (ms)

260.00

Runs Analysed

119

Last Updated

May 20, 2026, 02:08 AM

Key Insights

  • qwen-3.5-122b-a10b streams at 79.60 tokens/second on average across the last 119 benchmark runs.

  • Performance fluctuated by 113.37 tokens/second (142.4% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 260.00 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on May 20, 2026, 02:08 AM based on 119 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.

qwen-3.5-122b-a10b

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
deepinfraqwen-3.5-122b-a10b79.601.63115.00260.00

Frequently Asked Questions

The latest rolling average throughput is 79.60 tokens per second with an average time to first token of 260.00 ms across 119 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 02:08 AM.

Related Links