Wormhole n150 tt-metal: Whisper distil-large-v3 batch-1 TTFT
163.0 ms time-to-first-token, batch 1
Fields
id
benchmarks/ttmetal-n150-whisper-distil-large-v3-b1-ttftMetric
ttft_ms
Value
163
Unit
ms time-to-first-token, batch 1
Model
Whisper distil-large-v3
Methodology
VENDOR demo, same row as the 105.0 tok/s figure. Whisper distil-large-v3, single n150 (Wormhole), batch 1, TT-Metalium v0.65.0-dev20251208. ttft 163 ms is the time to the first output token after the input is received, one request.
Measured by
vendor
Reproducible
yes
notes
Vendor demo numbers, not a vLLM serving trace. The README states t/s = t/s/u * batch and that vLLM-server performance may differ. LLM rows use input sequence length 128 except Mamba, which accepts any length. Starred Blackhole figures carry the vendor's own caveat that the software is still under active optimization.
Notes
Vendor demo numbers, not a vLLM serving trace. The README states t/s = t/s/u * batch and that vLLM-server performance may differ. LLM rows use input sequence length 128 except Mamba, which accepts any length. Starred Blackhole figures carry the vendor's own caveat that the software is still under active optimization.