Graphcore C600 vs Graphcore Bow IPU
The Bow IPU delivers 25% more FP16 throughput than the C600 (350 vs 280 TFLOPS dense).
C600: Colossus MK2, 2022 Bow IPU: Colossus MK2, 2022
FP16 dense lead
+25%
Bow IPU: 350 vs 280 TFLOPS
Graphcore C600
Full specs →Architecture
Colossus MK2
Year
2022
TDP
185 W
Graphcore Bow IPU
Full specs →Architecture
Colossus MK2
Year
2022
Specifications
Architecture
Colossus MK2Colossus MK2
Launch Year
20222022
Form Factor
PCIe—
Memory
——
Memory Bandwidth
——
TDP
185 W—
Process Node
——
Spec C600 Bow IPU
Architecture Colossus MK2Colossus MK2
Launch Year 20222022
Form Factor PCIe—
Memory ——
Memory Bandwidth ——
TDP 185 W—
Process Node ——
Performance (TFLOPS)
FP64
No verified data available No verified data available
FP32
No verified data available87 TFLOPS
TF32
No verified data available No verified data available
BF16
No verified data available No verified data available
FP16
280 TFLOPS 350 TFLOPS
FP8
560 TFLOPS No verified data available
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
No verified data available No verified data available
Precision C600 Bow IPU
FP64 No verified data available No verified data available
FP32 No verified data available87 TFLOPS
TF32 No verified data available No verified data available
BF16 No verified data available No verified data available
FP16 280 TFLOPS 350 TFLOPS
FP8 560 TFLOPS No verified data available
FP6 No verified data available No verified data available
FP4 No verified data available No verified data available
INT8 No verified data available No verified data available
FLOPS by Precision
What actually differs
Both GPUs launched in 2022: the C600 on Colossus MK2 and the Bow IPU on Colossus MK2.
Dense throughput for the C600 against the Bow IPU: FP16 280 vs 350 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.
Frequently asked questions
Is the C600 faster than the Bow IPU?
At FP16 precision the Bow IPU reaches 350 TFLOPS dense against 280 TFLOPS for the C600. The performance table on this page lists every published precision for both GPUs.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.