Provider Snapshot
5
191.80
0.00
Jun 12, 2026
Key Takeaways
5 groq models are actively benchmarked with 658 total measurements across 427 benchmark runs.
GPT-oss-safeguard-20b leads the fleet with 319.00 tokens/second, while llama-4-scout delivers 133.00 tok/s.
Performance varies by 139.8% across the groq model lineup, indicating diverse optimization strategies for different use cases.
The groq model fleet shows varied performance characteristics (34.7% variation coefficient), reflecting diverse model architectures.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | GPT-oss-safeguard-20b | 319.00 | 61.20 | 599.00 | 0.00 |
| groq | llama-3.1-8b | 194.00 | 12.10 | 322.00 | 0.00 |
| groq | llama-3.3-70b | 158.00 | 46.10 | 239.00 | 0.00 |
| groq | qwen-3-32b | 155.00 | 48.50 | 221.00 | 0.00 |
| groq | llama-4-scout | 133.00 | 28.20 | 241.00 | 0.00 |
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 | llama-3.1-8b | 194.00 | 12.10 | 322.00 | 0.00 |
| groq | llama-3.3-70b | 158.00 | 46.10 | 239.00 | 0.00 |
| groq | llama-4-scout | 133.00 | 28.20 | 241.00 | 0.00 |
| groq | GPT-oss-safeguard-20b | 319.00 | 61.20 | 599.00 | 0.00 |
| groq | qwen-3-32b | 155.00 | 48.50 | 221.00 | 0.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, GPT-oss-safeguard-20b shows the highest average throughput among tracked groq models.
This provider summary aggregates 658 individual prompts measured across 427 monitoring runs over the past month.