Radeon Instinct MI60: specs and benchmarks

VS

Aggregate performance score

Radeon Instinct MI60 provides good gaming and benchmark performance at 26.33% of a leader's which is RTX PRO 5000 Blackwell.

Summary

AMD started Radeon Instinct MI60 sales 18 November 2018. This is a GCN 5.1 architecture desktop card based on 7 nm manufacturing process and primarily aimed at designers. 32 GB of HBM2 memory clocked at 1 GHz are supplied, and together with 4096 Bit memory interface this creates a bandwidth of 1,024 GB/s.

Compatibility-wise, this is a dual-slot graphics card attached via PCIe 4.0 x16 interface. Its manufacturer default version has a length of 267 mm. One 6-pin and one 8-pin connectors are required, and power consumption is at 300 Watt.

Primary details

Some basic facts about Radeon Instinct MI60: architecture, market segment, release date etc.

Place in the ranking234
Place by popularitynot in top-100
Power efficiency7.10of 100.00 (Radeon 890M)
ArchitectureGCN 5.1 (2018−2022)
GPU code nameVega 20
Market segmentWorkstation
Release date18 November 2018 (6 years ago)

Detailed specifications

Radeon Instinct MI60's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of Radeon Instinct MI60's performance, but for precise assessment you have to consider its benchmark and gaming test results.

Pipelines / CUDA cores4096of 960 (GeForce GTX 660)
Core clock speed1200 MHzof 980 (GeForce GT 755M SLI)
Boost clock speed1800 MHzof 1000 (HD Graphics (Haswell))
Number of transistors13,230 millionof 100,000 million (Data Center GPU Max 1100)
Manufacturing process technology7 nmof 0.003 MB (Arc Graphics 140V)
Power consumption (TDP)300 Wattof 235 (FirePro S9150)
Texture fill rate460.8of 1,968 (RTX PRO 6000 Blackwell)
Floating-point processing power14.75 TFLOPSof 126 (RTX PRO 6000 Blackwell)
ROPs64of 512 (Moore Threads MTT S4000)
TMUs256of 896 (Data Center GPU Max 1350)
L1 Cache1 MBof 64 MB (Data Center GPU Max 1550)
L2 Cache4 MBof 408 MB (Data Center GPU Max 1350)

Form factor & compatibility

This section provides details about the physical dimensions of Radeon Instinct MI60 and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).

InterfacePCIe 4.0 x16
Length267 mm
Width2-slot
Supplementary power connectors1x 6-pin + 1x 8-pin

VRAM capacity and type

Parameters of memory installed on Radeon Instinct MI60: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.

Memory typeHBM2
Maximum RAM amount32 GBof 288 GB (Radeon Instinct MI325X)
Memory bus width4096 Bitof 384 (GeForce GTX 980 Ti)
Memory clock speed1000 MHzof 16384000 MB (GeForce RTX 4050 Mobile)
Memory bandwidth1,024 GB/sof 983040 MB (GeForce RTX 5080)

Connectivity and outputs

Types and number of video connectors present on Radeon Instinct MI60. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.

Display ConnectorsNo outputs

API and SDK support

APIs supported by Radeon Instinct MI60, sometimes including their particular versions.

DirectX12 (12_1)
Shader Model6.4
OpenGL4.6
OpenCL2.0
Vulkan1.2.131

Benchmark performance

Synthetic benchmark performance of Radeon Instinct MI60. The combined score is measured on a 0-100 point scale.


Combined synthetic benchmark score

This is our combined benchmark score.

Instinct MI60
26.33

Passmark

This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.

Instinct MI60 11638
Samples: 1

GeekBench 5 OpenCL

Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.

Instinct MI60 91824

GeekBench 5 Vulkan

Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses Vulkan API by AMD & Khronos Group.

Instinct MI60 91798

Gaming performance

Let's see how good Radeon Instinct MI60 is for gaming. Particular gaming benchmark results are measured in frames per second. Comparisons with game system requirements are included, but remember that sometimes official requirements may reflect reality inaccurately.

Closest competitors

Radeon Instinct MI60's performance relative to its closest rivals among server graphics cards.


Quadro M6000 101.52
Tesla P40 101.44
Radeon Instinct MI60 100
A10G 99.85
Quadro P4000 98.21

NVIDIA equivalent

According to our data, the closest NVIDIA alternative to Radeon Instinct MI60 is A10G, which is nearly equal in speed and lower by 1 position in our ranking.

Here are some closest NVIDIA rivals to Radeon Instinct MI60:

Quadro M6000 101.52
Tesla P40 101.44
Radeon Instinct MI60 100
A10G 99.85
Quadro P4000 98.21
RTX A1000 92.71

Similar GPUs

Here is our recommendation of several graphics cards that are more or less close in performance to the one reviewed.

All comparisons with Radeon Instinct MI60

Community ratings

Here you can see the user rating of the graphics card, as well as rate it yourself.


3.2 6 votes

Rate Radeon Instinct MI60 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about Radeon Instinct MI60, agree or disagree with our ratings, or report errors or inaccuracies on the site.