llm-benchmarks
githubdrose.io

tenstorrent Provider Benchmarks


Measured over the last 30 days

Models Tracked
3
Avg Tokens / Second
21.27
Avg Time to First Token (ms)
3356.67
Last Updated
Nov 18, 2026

All tenstorrent models

3 live · one row per model · fastest first · 1 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Qwen3.8 27B21.7021.7021.702640.00
MiMo-V2.6-Flash21.6011.8041.003210.00
Qwen3 32B20.506.7534.304220.00

Frequently Asked Questions

Which tenstorrent model is fastest?
Based on recent tests, Qwen3.8 27B shows the highest average throughput among tracked tenstorrent models.
How many recent measurements feed this dashboard?
This provider summary aggregates 355 individual prompts measured across 354 monitoring runs over the past month.