Tenstorrent Wormhole n150 Falcon-7B token-gen (vendor b32)
18.5 tok/s per user at batch-32
Fields
id
benchmarks/comm-tt-wormhole-n150-falcon-7b-tgMetric
tok_s_per_user
Value
18.5
Unit
tok/s per user at batch-32
Model
Falcon-7B
Methodology
Vendor tt-metal model matrix, batch-32 decode, ISL=128
Measured by
vendor
Thermal state
unknown
notes
VENDOR-MEASURED. Falcon-7B is listed Complete on Wormhole only - not on Grayskull.
Notes
VENDOR-MEASURED. Falcon-7B is listed Complete on Wormhole only - not on Grayskull.