Flopper.io Flopper.io
Graphcore logo

Graphcore C600 vs Graphcore GC200

The C600 delivers 12% more FP16 throughput than the GC200 (280 vs 250 TFLOPS dense).

C600: Colossus MK2, 2022 GC200: Colossus MK2, 2020
FP16 dense lead
+12%
C600: 280 vs 250 TFLOPS
Download comparison sheet

Share this page

Graphcore C600 vs Graphcore GC200

A post with this link shows the card on the Image tab as its preview.

Post on X Share on LinkedIn
 Printable version →
Graphcore logo

Graphcore C600

Leads on FP16 Full specs →

What is the Graphcore C600?

The C600 is an ASIC from Graphcore on the Colossus MK2 architecture, an accelerator built for AI workloads. It is a PCIe add-in card, so it fits standard servers and workstations. C600 full specifications →

Can I rent the C600 in the cloud?

Flopper is not tracking any live rental listings for the C600 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the C600 compare with other accelerators?

This page sets the C600 against the GC200. The C600 is the newer generation of the two. Both are Graphcore parts. The compare tool builds the same comparison for any two parts in the catalogue. All GPU comparisons →

Where do the C600 figures come from?

Every C600 figure on this page traces to Graphcore's own datasheet or specification table. How Flopper verifies specifications →

Graphcore logo

Graphcore GC200

Full specs →

What is the Graphcore GC200?

The GC200 is an ASIC from Graphcore on the Colossus MK2 architecture, an accelerator built for AI workloads. GC200 full specifications →

Can I rent the GC200 in the cloud?

Flopper is not tracking any live rental listings for the GC200 yet. The provider directory lists the clouds that rent comparable accelerators on demand. GPU cloud providers →

How does the GC200 compare with other accelerators?

This page sets the GC200 against the C600. The GC200 is the older generation of the two. Both are Graphcore parts. Flopper also compares it head to head with the Bow IPU, across every published precision, memory and power. GC200 vs Bow IPU →

Where do the GC200 figures come from?

Every GC200 figure on this page traces to Graphcore's own datasheet or specification table. How Flopper verifies specifications →

Specifications

Graphcore logo
C600
Graphcore logo
GC200
Architecture
Colossus MK2Colossus MK2
Launch Year
20222020
Form Factor
PCIe—
Memory
——
Memory Bandwidth
——
TDP
185 W—
Process Node
—7nm

Performance (TFLOPS)

Graphcore logo
C600
Graphcore logo
GC200
No verified data available No verified data available
No verified data available63 TFLOPS
No verified data available No verified data available
No verified data available No verified data available
280 TFLOPS 250 TFLOPS
560 TFLOPS No verified data available
FP6
No verified data available No verified data available
No verified data available No verified data available
No verified data available No verified data available

Figures are dense. Where a vendor publishes a figure it sits under the dense one and never decides a winner. Hover any precision for its definition, or read the GPU glossary.

FLOPS by Precision

What actually differs

The C600 is the newer part: Colossus MK2 (2022) against the GC200's Colossus MK2 (2020).

Weight the FP8 and FP16 rows for LLM work and the FP64 row for HPC.

New to the terms? The glossary explains FP32, FP16, FP8, Sparsity and TFLOPS.

Frequently asked questions

Is the C600 faster than the GC200?

At FP16 precision the C600 reaches 280 TFLOPS dense against 250 TFLOPS for the GC200. The performance table on this page lists every published precision for both GPUs.

Which should you choose, the C600 or the GC200?

Choose the C600 for training and high-throughput inference: it has 12% more FP16 throughput than the GC200.

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.

Open in Full Compare Tool → C600 full specs GC200 full specs Estimate cluster cost in the calculator →

© 2026 Flopper.io - Compare the GPUs Powering AI