cerebras Provider Benchmarks

Comprehensive performance summary covering 5 models.

This provider hub highlights throughput and latency trends across every cerebras model monitored by LLM Benchmarks. Use it to compare hosting tiers, track regressions, and discover the fastest variants in the catalogue.

Visit cerebras Official Website

Provider Snapshot

Models Tracked

5

Median Tokens / Second

221.00

Median Time to First Token (ms)

0.61

Last Updated

Dec 26, 2025

Key Takeaways

  • 5 cerebras models are actively benchmarked with 4860 total measurements across 2598 benchmark runs.

  • qwen-3-32b leads the fleet with 266.00 tokens/second, while qwen-3-235b-instruct delivers 160.00 tok/s.

  • Performance varies by 66.3% across the cerebras model lineup, indicating diverse optimization strategies for different use cases.

  • Median time to first token across the fleet is 0.61 ms, showing excellent responsiveness for interactive applications.

  • The cerebras model fleet shows consistent performance characteristics (16.8% variation coefficient), indicating standardized infrastructure.

Fastest Models

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
cerebrasqwen-3-32b266.001.25373.000.52
cerebrasgpt-oss-120b244.004.92363.000.45
cerebrasllama-3.3-70b235.004.33340.000.35
cerebrasllama-3.1-8b200.003.26374.000.68
cerebrasqwen-3-235b-instruct160.001.67275.001.04

All Models

Complete list of all cerebras models tracked in the benchmark system. Click any model name to view detailed performance data.

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
cerebrasllama-3.1-8b200.003.26374.000.68
cerebrasllama-3.3-70b235.004.33340.000.35
cerebrasgpt-oss-120b244.004.92363.000.45
cerebrasqwen-3-32b266.001.25373.000.52
cerebrasqwen-3-235b-instruct160.001.67275.001.04

Featured Models

Frequently Asked Questions

Based on recent tests, qwen-3-32b shows the highest average throughput among tracked cerebras models.

This provider summary aggregates 4860 individual prompts measured across 2598 monitoring runs over the past month.