DEPLOYDatabase

Chip comparison

Google TPU v4 vs Groq LPU (Language Processing Unit)

Side-by-side specs

Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.

FieldGoogle TPU v4Groq LPU (Language Processing Unit)
Process nodeTSMC N7GlobalFoundries 14nm
TDP192 W375 W
Memory32 GB HBM20.23 GB SRAM (230 MB on-die)
Memory bandwidth1,200 GB/s80,000 GB/s
FP16 (dense)188 TFLOPS
BF16 (dense)275 TFLOPS
INT8 (dense)275 TOPS750 TOPS
Form factorOAM (per-chip in v4 pod)PCIe (GroqCard) / rack-scale GroqRack
Announced2021-05-182020-01-01
Released2022-05-012021-06-01

Robots running Google TPU v4

No robots publicly running it yet.

Robots running Groq LPU (Language Processing Unit)

No robots publicly running it yet.

Data centers with Groq LPU (Language Processing Unit)

No data centers publicly running it yet.

Common questions

Google TPU v4 vs Groq LPU (Language Processing Unit): which is faster for training?

Google TPU v4 has 1.46x the dense FP16/BF16 throughput of the other (Google TPU v4: 275 TFLOPS; Groq LPU (Language Processing Unit): 188 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Google TPU v4 vs Groq LPU (Language Processing Unit): which has more memory?

Google TPU v4 carries more HBM (Google TPU v4: 32 GB HBM2; Groq LPU (Language Processing Unit): 0.23 GB SRAM (230 MB on-die)). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Google TPU v4 vs Groq LPU (Language Processing Unit): which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v4 1.43 (275 ÷ 192 W); Groq LPU (Language Processing Unit) 0.50 (188 ÷ 375 W). Google TPU v4 wins at the die level; system-level efficiency also depends on cooling and interconnect.

Google TPU v4 vs Groq LPU (Language Processing Unit): which is more widely used?

Google TPU v4: 0 robots and 2 data centers publicly running it. Groq LPU (Language Processing Unit): 0 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.

See also: every chip comparison · Google TPU v4 full page · Groq LPU (Language Processing Unit) full page.