Provider Snapshot
6
201.67
325.00
Mar 26, 2026
Key Takeaways
6 groq models are actively benchmarked with 1296 total measurements across 699 benchmark runs.
llama-3.1-8b leads the fleet with 296.00 tokens/second, while kimi-k2 delivers 127.00 tok/s.
Performance varies by 133.1% across the groq model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 325.00 ms, showing excellent responsiveness for interactive applications.
The groq model fleet shows consistent performance characteristics (25.0% variation coefficient), indicating standardized infrastructure.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | llama-3.1-8b | 296.00 | 130.00 | 450.00 | 100.00 |
| groq | llama-4-maverick | 213.00 | 1.07 | 307.00 | 840.00 |
| groq | qwen-3-32b | 205.00 | 15.40 | 287.00 | 200.00 |
| groq | llama-4-scout | 186.00 | 51.60 | 333.00 | 260.00 |
| groq | llama-3.3-70b | 183.00 | 40.80 | 340.00 | 160.00 |
| groq | kimi-k2 | 127.00 | 12.20 | 215.00 | 390.00 |
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 | kimi-k2 | 127.00 | 12.20 | 215.00 | 390.00 |
| groq | llama-4-scout | 186.00 | 51.60 | 333.00 | 260.00 |
| groq | qwen-3-32b | 205.00 | 15.40 | 287.00 | 200.00 |
| groq | llama-4-maverick | 213.00 | 1.07 | 307.00 | 840.00 |
| groq | llama-3.3-70b | 183.00 | 40.80 | 340.00 | 160.00 |
| groq | llama-3.1-8b | 296.00 | 130.00 | 450.00 | 100.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, llama-3.1-8b shows the highest average throughput among tracked groq models.
This provider summary aggregates 1296 individual prompts measured across 699 monitoring runs over the past month.