OVERALL
ALTERNATIVES
SPECS
VS AVERAGE
REVIEWS
Scored using Graphics cards Methodology v3.0
Graphics cards Methodology v3.0
Mathematical & Unbiased Scoring
Products in this category are scored under Frontum Graphics cards Methodology v3.0: the technical score from the specifications is the base, and independent expert and video reviews (up to ±0.5 points), owner opinions (up to ±0.3) and best-of lists (up to +0.3) move it up or down.
Explore Graphics cards Methodology v3.0

AMD Radeon Instinct MI60 review: 117 specs compared

Avg. price:~£160VRAM:32 GBMemory bus width:4096 bitThermal Design Power (TDP):300 W

AMD Radeon Instinct MI60 Review: Compare 117 technical specifications and 1 expert and video reviews to see how this product ranks in the Graphics cards category and whether it is worth buying.

6.8/10

Overall score

Score
6.8/ 10
✕
What it is
Our main score for this model, 1–10. It combines specs, expert reviews, best-of lists and owners.
How we count it
Parts: Technical score 40%, Reviews score 25%, List score 25%, Sentiment score 10%
Marks: Each part gets a mark out of 10. For reviews, lists and owners, a typical model in this category gets about 8 and the best one gets 10.
No data yet: A part with no data shows "?". It counts as the mark of a weaker model in this category (4 in 5 models with data score higher). This way, models with reviews, lists and owners usually come out ahead.
Score distribution
â–¼
<55-66-77-88-99-10
â–¼ Worse than 73% of models
Score components

40%

6.4

Technical score

25%

6.4

Reviews score

25%

?

List scoreNot enough data yet, so we use 7.5, the mark of a weaker model in this category

10%

?

Sentiment scoreNot enough data yet, so we use 7.8, the mark of a weaker model in this category

â–¼Worse than 73% of graphics cards
7.7

Value for money

Value for money
7.7/ 10
✕
What it is
An indicator that combines the graphics card's overall rating with its cost.
When it matters
When you are looking for a graphics card that offers a strong balance of performance, features, and price.
Score distribution
â–¼
<55-66-77-88-99-10
â–² Better than 75% of models
Score components

70%

6.8

Overall score

30%

9.7

Price

â–²Better than 75%
6.4

Technical score

Technical score
6.4/ 10
✕
What it is
How good the specs are compared with the other models in this category, 1–10.
How we count it
Areas: We rate the specs in each area against the other models in this category.
Weighting: The areas that matter most to buyers count more. The shares are shown under Score components.
Share: The technical score is 40% of the overall score.
Score distribution
â–¼
<55-66-77-88-99-10
â–¼ Worse than 63% of models
Score components

44%

5.2

Performance

24%

8.0

Memory

12%

5.1

Power

11%

8.1

Features

5%

8.2

Design

4%

5.4

Connectivity

â–¼Worse than 63%
6.4

Reviews score

Reviews score
6.4/ 10
✕
What it is
Average grade from independent test sites, magazines and video reviewers, 1–10.
How we count it
Grades: Each review's own score is converted to 1–10; without one, we grade the review ourselves. Big test sites count more, short reviews half as much as full tests. A video review counts half.
Score: The average grade is 80% of the review mark; the number of reviews is the other 20% (1 review = 5, the typical number in this category = 8, the most-reviewed model = 10).
Enough data: With few reviews, the average grade is pulled toward the typical grade of this category. No reviews yet: 7.6 for now.
Share: Reviews count 25% of the overall score.
Score distribution
â–¼
<55-66-77-88-99-10
â–¼ Worse than 77% of models

6.4

Mark 7.1 is below the typical mark 7.9 of this category, so it cannot lift the score above the technical score

80%

7.6

Average grade

20%

5.0

Popularity

Grades by review (1)
1 video review, counting half as much as a written test. Reviews count 25% of the overall score.
User ratings collected online are not part of this score.
â–¼Worse than 77%
?

List score

List score
7.5/ 10
✕
What it is
How often independent test sites, magazines and video reviewers put this model in their best-of lists for this category.
How we count it
Points: The model in the most lists of this category gets 10; the others get 8 to 10 in proportion. In no list yet: 7.5. Lists count 25% of the overall score.
Enough data: Every list counts, even a single one. With fewer than 5 best-of lists in the category, this part is left out.
Lists with this model (0)
Not in any best-of list yet, so this part counts as 7.5. Models in a list get 8 to 10.
Not in any best-of list yet
  • No image
No image
Where to buy
    N/A~ £160
Best rankings
Available: ranking among products currently available (including other versions of this product).All: ranking among all products in the database.
Loading category ranking...

Technical Specifications of graphics card AMD Radeon Instinct MI60

Technical score
Technical score
6.4/ 10
✕
What it is
How good the specs are compared with the other models in this category, 1–10.
How we count it
Areas: We rate the specs in each area against the other models in this category.
Weighting: The areas that matter most to buyers count more. The shares are shown under Score components.
Share: The technical score is 40% of the overall score.
Score distribution
â–¼
<55-66-77-88-99-10
â–¼ Worse than 63% of models
Score components:

44%

5.2

Performance

24%

8.0

Memory

12%

5.1

Power

11%

8.1

Features

5%

8.2

Design

4%

5.4

Connectivity

6.4
Reviews score
6.4
List score
?
Value for money
Value for money
7.7/ 10
✕
What it is
An indicator that combines the graphics card's overall rating with its cost.
When it matters
When you are looking for a graphics card that offers a strong balance of performance, features, and price.
Score distribution
â–¼
<55-66-77-88-99-10
â–² Better than 75% of models
Score components:

70%

6.8

Overall score

30%

9.7

Price

7.7
3DMark Time Spy benchmark score
?
3DMark Port Royal score
0 points
Market range: <0 points – >22.4k points
This graphics card scores 0 points in 3DMark Port Royal, which is lower than 83.1% of graphics cards and equal to 16.9% of graphics cards.
PassMark (G3D) result
11,638 points
Market range: <7.7k points – >36k points
This graphics card scores 11,638 points in PassMark G3D, which is lower than 81.7% of graphics cards.
PassMark (DirectCompute) result
6,123 points
Market range: <3.1k points – >26.3k points
This graphics card scores 6,123 points in PassMark DirectCompute, which is lower than 78.6% of graphics cards.
FP32 performance
14.75 TFLOPS
Market range: <3.94 TFLOPS – >56.3 TFLOPS
This graphics card delivers 14.75 TFLOPS FP32 performance, which is lower than that of 64.6% of graphics cards.
Show more
VRAM
32 GB
Market range: <4 GB – >16 GB
This graphics card has 32 GB of VRAM, which is more than 96.6% of graphics cards and equal to 3.1% of graphics cards.
Memory type
HBM2
This graphics card uses HBM2 memory, which is newer than on 56.7% of graphics cards and equal to 0.4% of graphics cards.
Memory bus width
4,096 bit
Market range: <128 bit – >384 bit
This graphics card uses a 4,096 bit memory bus, which is wider than that of 99.9% of graphics cards and equal to that of 0.1% of graphics cards.
Maximum memory bandwidth
1,024 GB/s
Market range: <168 GB/s – >960 GB/s
This graphics card reaches 1,024 GB/s memory bandwidth, which is higher than that of 97.2% of graphics cards and equal to that of 0.1% of graphics cards.
Effective memory speed
2000 MHz
Market range: <7k MHz – >28k MHz
This graphics card reaches an effective memory speed of 2000 MHz, which is slower than that of 98.4% of graphics cards.
Show more
PCI Express (PCIe) version
4
This graphics card supports PCIe 4, which is newer than on 22.5% of graphics cards and equal to 50.5% of graphics cards.
PCIe lanes
x16
This graphics card uses x16 PCIe lanes, which is more than 24.1% of graphics cards and equal to 75.9% of graphics cards.
DirectX version
12.1
This graphics card supports DirectX 12.1, which is older than on 77.2% of graphics cards and equal to 4.5% of graphics cards.
Vulkan version
1.3
This graphics card supports Vulkan 1.3, which is older than on 79.2% of graphics cards and equal to 15.6% of graphics cards.
OpenGL version
4.6
This graphics card supports OpenGL 4.6, which is more advanced than on 2% of graphics cards and equal to 98% of graphics cards.
Show more
Max displays supported
1
Market range: <4 – >4
This graphics card supports up to 1 displays, which is fewer than 99.9% of graphics cards and equal to 0.1% of graphics cards.
Max digital resolution
?
DisplayPort outputs
1
Market range: <1 – >3
This graphics card offers 1 DisplayPort outputs, which is fewer than 88.1% of graphics cards and equal to 8.7% of graphics cards.
DisplayPort version
1.4a
This graphics card supports DisplayPort 1.4a, which is more advanced than on 19.3% of graphics cards and equal to 46.3% of graphics cards.
DisplayPort link rates
8.1 Gbps
Market range: <5.4 Gbps – >80 Gbps
This graphics card supports DisplayPort link rates up to 8.1 Gbps, which is slower than on 65.3% of graphics cards and equal to 22.5% of graphics cards.
Show more
Thermal Design Power (TDP)
300 W
Market range: <86 W – >360 W
This graphics card has a TDP of 300 W, which is higher than that of 72.1% of graphics cards and equal to that of 6.4% of graphics cards.
Power consumption while under peak load
300 W
Market range: <106 W – >365 W
This graphics card draws 300 W under peak load, which is higher than 70.3% of graphics cards and equal to 4.4% of graphics cards.
Recommended PSU wattage
700 W
Market range: <450 W – >850 W
This graphics card recommends a 700 W PSU, which is higher than that of 60.8% of graphics cards and equal to that of 4.6% of graphics cards.
Board power limit
300 W
Market range: <107 W – >400 W
This graphics card has a board power limit of 300 W, which is higher than that of 68.1% of graphics cards and equal to that of 5.5% of graphics cards.
PCIe power spec
300 W
Show more
Size
267x 111x 41 mm
Length
267 mm
Market range: <200 mm – >337 mm
This graphics card is 267 mm long, which is shorter than 59.3% of graphics cards and equal in length to 3.5% of graphics cards.
Height
111 mm
Market range: <109 mm – >146 mm
This graphics card is 111 mm tall, which is shorter than 83.6% of graphics cards and equal in height to 5.1% of graphics cards.
Slot width
2 slot/s
Market range: <2 slot/s – >3.25 slot/s
This graphics card occupies 2 slot/s, which is slimmer than 52.4% of graphics cards and equal in width to 43.4% of graphics cards.
Weight
1,250 g
Market range: <541 g – >2k g
This graphics card weighs 1,250 g, which is heavier than 63.6% of Graphics cards and equal to 0.3% of Graphics cards.
Show more

AMD Radeon Instinct MI60 vs the average graphics card

246810TotalPerformanceMemoryFeaturesConnectivityPowerDesign
  • 20 GB more VRAM
    This graphics card has more VRAM than the average graphics card (32 GB vs 12 GB). The average graphics card has 12 GB VRAM.
    32 GB vs 12 GB
  • 2.29x higher memory bandwidth
    This graphics card has a higher memory bandwidth than the average graphics card (1,024 GB/s vs 448 GB/s). The average graphics card has a memory bandwidth of 448 GB/s.
    1,024 GB/s vs 448 GB/s
  • 3,904 bit wider memory bus
    This graphics card has a wider memory bus than the average graphics card (4,096 bit vs 192 bit). The average graphics card has a memory bus width of 192 bit.
    4,096 bit vs 192 bit
  • 496 more AI cores
    This graphics card has more AI cores than the average graphics card (640 vs 144). The average graphics card has 144 AI cores.
    640 vs 144
  • 24 more compute units
    This graphics card has more compute units than the average graphics card (64 vs 40). The average graphics card has 40 compute units.
    64 vs 40
  • Supports ECC memory
    This graphics card supports ECC memory, the average graphics card does not.
  • 72 more TMUs
    This graphics card has more TMUs than the average graphics card (256 vs 184). The average graphics card has 184 TMUs.
    256 vs 184
  • 14 mm lower card height
    This graphics card is shorter than the average graphics card (111 mm vs 125 mm). The average graphics card has a height of 125 mm.
    111 mm vs 125 mm
  • 3.25x cheaper
    AMD Radeon Instinct MI60 is cheaper than the average graphics card (£160 vs £520).
    £160 vs £520
  • 496 more AI cores
    This graphics card has more AI cores than the average graphics card (640 vs 144). The average graphics card has 144 AI cores.
    640 vs 144
  • 24 more compute units
    This graphics card has more compute units than the average graphics card (64 vs 40). The average graphics card has 40 compute units.
    64 vs 40
  • 72 more TMUs
    This graphics card has more TMUs than the average graphics card (256 vs 184). The average graphics card has 184 TMUs.
    256 vs 184
  • More FP64 throughput
    This graphics card has a better FP64 ratio than the average graphics card (1:2 vs 1:64).
    1:2 vs 1:64
  • 15.42x higher FP64 performance
    This graphics card has a higher FP64 performance than the average graphics card (7.4 TFLOPS vs 0.48 TFLOPS). The average graphics card has FP64 performance of 0.48 TFLOPS.
    7.4 TFLOPS vs 0.48 TFLOPS
  • 21.9% higher texture rate
    This graphics card has a higher texture rate than the average graphics card (460.8 GTexel/s vs 378 GTexel/s). The average graphics card has a texture rate of 378 GTexel/s.
    460.8 GTexel/s vs 378 GTexel/s
  • 2.29x higher memory bandwidth
    This graphics card has a higher memory bandwidth than the average graphics card (1,024 GB/s vs 448 GB/s). The average graphics card has a memory bandwidth of 448 GB/s.
    1,024 GB/s vs 448 GB/s
  • 20 GB more VRAM
    This graphics card has more VRAM than the average graphics card (32 GB vs 12 GB). The average graphics card has 12 GB VRAM.
    32 GB vs 12 GB
  • 3,904 bit wider memory bus
    This graphics card has a wider memory bus than the average graphics card (4,096 bit vs 192 bit). The average graphics card has a memory bus width of 192 bit.
    4,096 bit vs 192 bit
  • Supports ECC memory
    This graphics card supports ECC memory, the average graphics card does not.
  • 4 more GPUs supported
    This graphics card supports more GPUs in multi-GPU mode than the average graphics card (4 vs 0). The average graphics card supports 0 GPUs in multi-GPU mode.
    4 vs 0
  • Supports virtual GPU
    This graphics card supports virtual GPU features, the average graphics card does not.
  • Supports multi-GPU linking
    This graphics card supports multi-GPU linking, the average graphics card does not.
  • 14 mm lower card height
    This graphics card is shorter than the average graphics card (111 mm vs 125 mm). The average graphics card has a height of 125 mm.
    111 mm vs 125 mm
  • 0.5 slot/s slimmer design
    This graphics card occupies fewer slots than the average graphics card (2 slot/s vs 2.5 slot/s). The average graphics card occupies 2.5 slot/s.
    2 slot/s vs 2.5 slot/s
  • 40 fewer ray tracing cores
    This graphics card has fewer ray tracing cores than the average graphics card (0 vs 40). The average graphics card has 40 ray tracing cores.
    0 vs 40
  • 3 fewer fans
    This graphics card has fewer fans than the average graphics card (0 vs 3).
    0 vs 3
  • 28.1% lower boost clock speed
    This graphics card has a lower boost GPU clock than the average graphics card (1,800 MHz vs 2,505 MHz). The average graphics card has a boost GPU clock of 2,505 MHz.
    1,800 MHz vs 2,505 MHz
  • Less advanced frame generation
    This graphics card has less advanced frame generation than the average graphics card (no vs multi frame generation).
  • No CUDA support
    This graphics card does not support CUDA, the average graphics card does.
  • 37.5% lower base clock speed
    This graphics card has a lower base GPU clock than the average graphics card (1,200 MHz vs 1920 MHz). The average graphics card has a base GPU clock of 1920 MHz.
    1,200 MHz vs 1,920 MHz
  • 89.5% slower memory speed
    This graphics card has a lower effective memory speed than the average graphics card (2000 MHz vs 19,000 MHz). The average graphics card reaches an effective memory speed of 19,000 MHz.
    2,000 MHz vs 19,000 MHz
  • No DLSS support
    This graphics card does not support DLSS, the average graphics card does.
  • 11.1% lower review score
    Reviews score
    6.4/ 10
    ✕
    What it is
    Average grade from independent test sites, magazines and video reviewers, 1–10.
    How we count it
    Grades: Each review's own score is converted to 1–10; without one, we grade the review ourselves. Big test sites count more, short reviews half as much as full tests. A video review counts half.
    Score: The average grade is 80% of the review mark; the number of reviews is the other 20% (1 review = 5, the typical number in this category = 8, the most-reviewed model = 10).
    Enough data: With few reviews, the average grade is pulled toward the typical grade of this category. No reviews yet: 7.6 for now.
    Share: Reviews count 25% of the overall score.
    Score distribution
    â–¼
    <55-66-77-88-99-10
    â–¼ Worse than 77% of models

    6.4

    Mark 7.1 is below the typical mark 7.9 of this category, so it cannot lift the score above the technical score

    80%

    7.6

    Average grade

    20%

    5.0

    Popularity

    Grades by review (1)
    1 video review, counting half as much as a written test. Reviews count 25% of the overall score.
    User ratings collected online are not part of this score.
    6.4 vs 7.2
  • 40 fewer ray tracing cores
    This graphics card has fewer ray tracing cores than the average graphics card (0 vs 40). The average graphics card has 40 ray tracing cores.
    0 vs 40
  • 28.1% lower boost clock speed
    This graphics card has a lower boost GPU clock than the average graphics card (1,800 MHz vs 2,505 MHz). The average graphics card has a boost GPU clock of 2,505 MHz.
    1,800 MHz vs 2,505 MHz
  • No CUDA support
    This graphics card does not support CUDA, the average graphics card does.
  • 37.5% lower base clock speed
    This graphics card has a lower base GPU clock than the average graphics card (1,200 MHz vs 1920 MHz). The average graphics card has a base GPU clock of 1920 MHz.
    1,200 MHz vs 1,920 MHz
  • 28.6% lower pixel rate
    This graphics card has a lower pixel rate than the average graphics card (115.2 GPixel/s vs 161.3 GPixel/s). The average graphics card has a pixel rate of 161.3 GPixel/s.
    115.2 GPixel/s vs 161.3 GPixel/s
  • 5 years older
    This graphics card was released earlier than the average graphics card (2018 vs 2023).
    November 2018
    2018 vs 2023
  • 48.6% lower PassMark score
    This graphics card has a lower PassMark score than the average graphics card (11,638 points vs 22,638 points). The average graphics card has a PassMark score of 22,638 points.
    11,638 points vs 22,638 points
  • 34.7% lower FP32 performance
    This graphics card has a lower FP32 performance than the average graphics card (14.8 TFLOPS vs 22.6 TFLOPS). The average graphics card has FP32 performance of 22.6 TFLOPS.
    14.75 TFLOPS vs 22.6 TFLOPS
  • 49.3% lower compute score
    This graphics card has a lower compute score than the average graphics card (6,123 points vs 12,70.5 points). The average graphics card has a compute score of 12,070.5 points.
    6,123 points vs 12,070.5 points
  • 89.5% slower memory speed
    This graphics card has a lower effective memory speed than the average graphics card (2000 MHz vs 19,000 MHz). The average graphics card reaches an effective memory speed of 19,000 MHz.
    2,000 MHz vs 19,000 MHz
  • 42.9% slower VRAM clock
    This graphics card has a lower VRAM clock than the average graphics card (1,000 MHz vs 1,750 MHz). The average graphics card runs its VRAM at 1,750 MHz.
    1,000 MHz vs 1,750 MHz
  • 83.3% smaller L2 cache
    This graphics card has fewer L2 cache than the average graphics card (4 MB vs 24 MB). The average graphics card has 24 MB L2 cache.
    4 MB vs 24 MB
  • 87.5% smaller L1 cache
    This graphics card has fewer L1 cache than the average graphics card (16 KB vs 128 KB). The average graphics card has 128 KB L1 cache.
    16 KB vs 128 KB
  • Less advanced frame generation
    This graphics card has less advanced frame generation than the average graphics card (no vs multi frame generation).
  • No DLSS support
    This graphics card does not support DLSS, the average graphics card does.
  • No ray tracing
    This graphics card does not support ray tracing, the average graphics card does.
  • 40% larger process node
    This graphics card uses a larger manufacturing process than the average graphics card (7 nm vs 5 nm). The average graphics card uses a manufacturing process of 5 nm.
    7 nm vs 5 nm
  • No XeSS support
    This graphics card does not support XeSS, the average graphics card does.
  • No mesh shaders
    This graphics card does not support mesh shaders, the average graphics card does.
  • No DirectStorage support
    This graphics card does not support DirectStorage, the average graphics card does.
  • Older Vulkan version
    This graphics card supports an older Vulkan version than the average graphics card (1.3 vs 1.4).
    1.3 vs 1.4
  • Lower VRS tier
    This graphics card supports a lower VRS tier than the average graphics card (Tier 1 vs Tier 2).
    Tier 1 vs Tier 2
  • Older DirectX version
    This graphics card supports an older DirectX version than the average graphics card (12.1 vs 12 Ultimate).
    12.1 vs 12 Ultimate
  • Older OpenCL version
    This graphics card supports an older OpenCL version than the average graphics card (2 vs 3).
    2 vs 3
  • No sampler feedback
    This graphics card does not support sampler feedback, the average graphics card does.
  • Older shader model
    This graphics card supports an older shader model than the average graphics card (6.7 vs 6.8).
    6.7 vs 6.8
  • Older FSR version
    This graphics card supports an older FSR version than the average graphics card (1 vs 3.1).
    1 vs 3.1
  • 2 fewer DisplayPort outputs
    This graphics card has fewer DisplayPort outputs than the average graphics card (1 vs 3). The average graphics card has 3 DisplayPort outputs.
    1 vs 3
  • No AV1 encoding
    This graphics card does not support AV1 encoding, the average graphics card does.
  • 3 fewer displays supported
    This graphics card supports fewer displays than the average graphics card (1 vs 4). The average graphics card supports 4 displays.
    1 vs 4
  • No VRR support
    This graphics card does not support VRR, the average graphics card does.
  • More basic codec support
    This graphics card encodes more basic formats than the average graphics card (H.264/H.265 vs H.264/H.265/AV1/VP9).
    H.264/H.265 vs H.264/H.265/AV1/VP9
  • No HDMI output
    This graphics card does not include HDMI output, the average graphics card does.
  • Not VR ready
    This graphics card is not VR ready, while the average graphics card is.
  • 2 fewer monitors per output type
    This graphics card supports fewer monitors per output type than the average graphics card (1 vs 3). The average graphics card supports 3 monitors per output type.
    1 vs 3
  • No 3D output
    This graphics card does not support 3D output, the average graphics card does.
  • 62.5% lower DisplayPort bandwidth
    This graphics card has a lower DisplayPort bandwidth than the average graphics card (8.1 Gbps vs 21.6 Gbps). The average graphics card has DisplayPort bandwidth of 21.6 Gbps.
    8.1 Gbps vs 21.6 Gbps
  • 3 fewer fans
    This graphics card has fewer fans than the average graphics card (0 vs 3).
    0 vs 3
  • No overclocking support
    This graphics card does not support overclocking, the average graphics card does.
  • No dual BIOS
    This graphics card does not include dual BIOS, the average graphics card does.
  • No fan stop
    This graphics card does not support fan stop, the average graphics card does.
  • 39.5% higher TDP
    This graphics card has a higher TDP than the average graphics card (300 W vs 215 W). The average graphics card has a TDP of 215 W.
    300 W vs 215 W
  • 15 °C lower thermal ceiling
    This graphics card has a lower thermal ceiling than the average graphics card (110 °C vs 95 °C). The average graphics card has a thermal ceiling of 95 °C.
    110 °C vs 95 °C
  • 36.4% higher board power limit
    This graphics card has a higher board power limit than the average graphics card (300 W vs 220 W). The average graphics card has a board power limit of 220 W.
    300 W vs 220 W
  • 17 °C higher load temperature
    This graphics card has a higher load temperature than the average graphics card (84 °C vs 67 °C). The average graphics card has a load temperature of 67 °C.
    84 °C vs 67 °C
  • 7.7% higher PSU requirement
    This graphics card has a higher PSU requirement than the average graphics card (700 W vs 650 W). The average graphics card has a PSU requirement of 650 W.
    700 W vs 650 W
  • 58.3% higher idle power draw
    This graphics card has a higher idle power draw than the average graphics card (19 W vs 12 W). The average graphics card has an idle power draw of 12 W.
    19 W vs 12 W
  • 36.4% higher peak power draw
    This graphics card has a higher peak power draw than the average graphics card (300 W vs 220 W). The average graphics card has a peak power draw of 220 W.
    300 W vs 220 W
  • No backplate
    This graphics card does not include a backplate, the average graphics card does.
  • No RGB lighting
    This graphics card does not include RGB lighting, the average graphics card does.

Video reviews

Hands-on testing, unboxing, and real-world video evaluations

5.0
brandon coin
≈ estimated
23/11/2021
Hands-on review · mining tests and overclocking
Verdict
AMD Radeon Instinct MI60 is still a poor buy, given the high price and weak return on investment.
Shop video
Overview video
Overview video

Third-party reviews

What customers like about AMD Radeon Instinct MI60

  • High VRAM capacity (32GB HBM2) makes it excellent for large AI models and LLM inference.
  • Very high memory bandwidth (1TB/s) provides fast data throughput for computational tasks.
  • Excellent value for budget-conscious AI/Blender workstations when purchased on the used market.
  • Full ECC memory support and high double-precision (FP64) performance for scientific workloads.
  • Compatible with ROCm and Vulkan back-ends, supporting local LLM tools like llama.cpp.

What customers don't like about AMD Radeon Instinct MI60

  • Passive cooling design requires specialized server cases or custom-shrouded fans to prevent chronic overheating.
  • Lack of native display outputs typically requires a secondary GPU or integrated graphics for a monitor.
  • High power consumption (300W TDP) often requires specialized 8-pin PCIe power setups or secondary power supplies.
  • Complex software setup; some users reported significant difficulty compiling ROCm for this specific card.
  • No support for FlashAttention2 due to the lack of dedicated matrix multiplication (Tensor) cores.

Verdict

The AMD Radeon Instinct MI60 is a high-performance server-grade accelerator built on a 7nm process with the Vega 20 architecture, featuring 64 compute units and 4,096 stream processors. It is equipped with 32GB of HBM2 ECC memory and a massive 4,096-bit memory bus, delivering a record-setting 1 TB/s of memory bandwidth and 7.4 TFLOPS of peak double-precision (FP64) performance. Key pros include its exceptional memory throughput, support for PCIe 4.0, and high efficiency for AI and HPC workloads; however, its cons include a high 300W TDP that requires robust passive or custom cooling, and a lack of standard display outputs, as it is intended for data center use rather than gaming.

Compare AMD Radeon Instinct MI60 with other products in the Graphics cards category

1Product to compare no. 1
VS
2Product to compare no. 2
VS
3Product to compare no. 3 (optional)

Graphic comparison of AMD Radeon Instinct MI60 and other products in the Graphics cards category

No results found