Measured on bedrock
1360 runs- Avg Tokens / Second
- 85.20
- Avg Time to First Token (ms)
- 370.00
- Runs Analysed
- 1360
- Last Updated
- Aug 9, 2026, 08:12 AM
Throughput distribution
- llama-3.3-70b bedrock85 tok/s
Visible-token throughput, same basis as the table · curves normalised per model
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 118 tok/s (99th percentile) · dashed rule is the model's own mean
Every provider serving this model
1 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-3.3-70b | 85.20 | 4.60 | 122.00 | 370.00 |
Frequently Asked Questions
How fast is llama-3.3-70b?
The latest rolling average throughput is 85.20 tokens per second with an average time to first token of 370.00 ms across 1360 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 9, 2026, 08:12 AM.