Provider Snapshot
6
154.17
0.39
Oct 18, 2025
Key Takeaways
6 groq models are actively benchmarked with 4900 total measurements across 3831 benchmark runs.
gemma-2-9b leads the fleet with 235.00 tokens/second, while deepseek-r1 delivers 104.00 tok/s.
Performance varies by 126.0% across the groq model lineup, indicating diverse optimization strategies for different use cases.
Median time to first token across the fleet is 0.39 ms, showing excellent responsiveness for interactive applications.
The groq model fleet shows consistent performance characteristics (25.8% variation coefficient), indicating standardized infrastructure.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | gemma-2-9b | 235.00 | 28.90 | 285.00 | 0.17 |
| groq | llama-3.1-8b | 155.00 | 4.93 | 202.00 | 0.36 |
| groq | qwen-3-32b | 149.00 | 2.15 | 310.00 | 0.39 |
| groq | llama-4-maverick | 146.00 | 3.97 | 343.00 | 0.60 |
| groq | llama-3.3-70b | 136.00 | 4.54 | 274.00 | 0.43 |
| groq | deepseek-r1 | 104.00 | 11.40 | 137.00 | 0.36 |
All Models
Complete list of all groq models tracked in the benchmark system. Click any model name to view detailed performance data.
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | llama-3.1-8b | 155.00 | 4.93 | 202.00 | 0.36 |
| groq | llama-3.3-70b | 136.00 | 4.54 | 274.00 | 0.43 |
| groq | gemma-2-9b | 235.00 | 28.90 | 285.00 | 0.17 |
| groq | llama-4-maverick | 146.00 | 3.97 | 343.00 | 0.60 |
| groq | qwen-3-32b | 149.00 | 2.15 | 310.00 | 0.39 |
| groq | deepseek-r1 | 104.00 | 11.40 | 137.00 | 0.36 |
Featured Models
Frequently Asked Questions
Based on recent tests, gemma-2-9b shows the highest average throughput among tracked groq models.
This provider summary aggregates 4900 individual prompts measured across 3831 monitoring runs over the past month.