Provider Snapshot
6
182.00
0.00
Jun 25, 2026
Key Takeaways
6 groq models are actively benchmarked with 1730 total measurements across 1330 benchmark runs.
GPT-oss-safeguard-20b leads the fleet with 300.00 tokens/second, while llama-4-scout delivers 127.00 tok/s.
Performance varies by 136.2% across the groq model lineup, indicating diverse optimization strategies for different use cases.
The groq model fleet shows varied performance characteristics (32.9% variation coefficient), reflecting diverse model architectures.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | GPT-oss-safeguard-20b | 300.00 | 35.20 | 703.00 | 0.00 |
| groq | llama-3.1-8b | 216.00 | 12.10 | 336.00 | 0.00 |
| groq | qwen-3-32b | 158.00 | 25.40 | 233.00 | 0.00 |
| groq | llama-3.3-70b | 154.00 | 79.70 | 275.00 | 0.00 |
| groq | qwen3.6-27b | 137.00 | 31.50 | 321.00 | 0.00 |
| groq | llama-4-scout | 127.00 | 18.50 | 245.00 | 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 | 216.00 | 12.10 | 336.00 | 0.00 |
| groq | llama-3.3-70b | 154.00 | 79.70 | 275.00 | 0.00 |
| groq | llama-4-scout | 127.00 | 18.50 | 245.00 | 0.00 |
| groq | GPT-oss-safeguard-20b | 300.00 | 35.20 | 703.00 | 0.00 |
| groq | qwen-3-32b | 158.00 | 25.40 | 233.00 | 0.00 |
| groq | qwen3.6-27b | 137.00 | 31.50 | 321.00 | 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 1730 individual prompts measured across 1330 monitoring runs over the past month.