Tenstorrent Wormhole n150 Llama-3.2-1B token-gen (vendor b32)
80.5 tok/s per user at batch-32
Fields
id
benchmarks/comm-tt-wormhole-n150-llama32-1b-tgMetric
tok_s_per_user
Value
80.5
Unit
tok/s per user at batch-32
Model
Llama-3.2-1B
Methodology
Vendor tt-metal model matrix, batch-32 decode, ISL=128
Measured by
vendor
Thermal state
unknown
notes
VENDOR-MEASURED.
Notes
VENDOR-MEASURED.