Tenstorrent Wormhole n300 Qwen2.5-7B decode (vendor-measured, b32 TP2)
22.1 tok/s per user at batch-32; 707 tok/s aggregate
Fields
id
benchmarks/comm-tt-wormhole-n300-qwen25-7b-decodeMetric
tok_s_per_user
Value
22.1
Unit
tok/s per user at batch-32; 707 tok/s aggregate
Model
Qwen2.5-7B
Methodology
Vendor tt-metal model matrix, batch-32 decode ISL=128, n300 TP=2
Measured by
vendor
Thermal state
unknown