Measured on bedrock
415 runs- Avg Tokens / Second
- 46.80
- Avg Time to First Token (ms)
- 350.00
- Runs Analysed
- 415
- Last Updated
- Jul 16, 2026, 03:40 PM
Throughput distribution
- llama-3.2-90b bedrock47 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 51 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-3.2-90b | 46.80 | 30.80 | 49.90 | 350.00 |
Frequently Asked Questions
How fast is llama-3.2-90b?
The latest rolling average throughput is 46.80 tokens per second with an average time to first token of 350.00 ms across 415 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 16, 2026, 03:40 PM.