- Avg Tokens / Second
- 48.45
- Avg Time to First Token (ms)
- 695.00
- Runs Analysed
- 42
- Last Updated
- Sep 1, 2026, 03:16 AM
Throughput distribution
Throughput over time
Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 63 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn
Every provider serving this model
2 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cohere | Command R7B (12-2024) | 53.20 | 39.80 | 61.60 | 560.00 |
| cohere | Command R7B (12-2024) | 43.70 | 21.90 | 65.00 | 830.00 |
Frequently Asked Questions
How fast is Command R7B (12-2024)?
The latest rolling average throughput is 48.45 tokens per second with an average time to first token of 695.00 ms across 42 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 03:16 AM.