llm-benchmarks
githubdrose.io

mixtral-8x7b Benchmarks


Measured on bedrock

1367 runs
Avg Tokens / Second
73.10
Avg Time to First Token (ms)
240.00
Runs Analysed
1367
Last Updated
Aug 9, 2026, 09:58 PM

Throughput distribution

  • mixtral-8x7b bedrock73 tok/s
0255075100

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

mixtral-8x7bbedrock71tok/s

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 84 tok/s (99th percentile) · dashed rule is the model's own mean

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
bedrockmixtral-8x7b73.1019.3080.60240.00

Frequently Asked Questions

How fast is mixtral-8x7b?
The latest rolling average throughput is 73.10 tokens per second with an average time to first token of 240.00 ms across 1367 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, 09:58 PM.

Related models