llm-benchmarks
githubdrose.io

mixtral-8x7b Benchmarks


Measured on bedrock

1408 runs
Avg Tokens / Second
74.80
Decode Tokens / Second
99.10
Avg Time to First Token (ms)
220.00
Runs Analysed
1408
Last Updated
Sep 16, 2026, 05:16 PM

Throughput distribution

Throughput over time

mixtral-8x7bbedrock75tok/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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 85 tok/s (99th percentile) · dashed rule is the model's own mean

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
bedrockdirect74.8020.8080.90220.001408

Frequently Asked Questions

How fast is mixtral-8x7b?
The latest rolling average throughput is 74.80 tokens per second with an average time to first token of 220.00 ms across 1408 recent runs. Once tokens are flowing the decoder delivers about 99.10 tokens per second, measured from the gaps between stream chunks with time to first token and reasoning excluded.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 16, 2026, 05:16 PM.

Related models