RADEON

AMD Radeon 860M

AMD graphics card specifications and benchmark scores

VRAM
3000
MHz Boost
15W
TDP
Bus Width
Ray Tracing

At a Glance

AMD
VRAM System Shared
Boost Clock 3,000 MHz
Shaders 512
TDP 15W
Memory Type System Shared
RT Cores 8
Architecture RDNA 3.5
nm
Process 4 nm
Released Mar 2025

AMD Radeon 860M Specifications

GPU Core

Shader units and compute resources

The AMD Radeon 860M GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.

Shading Units
512
Shaders
512
TMUs
32
ROPs
16
Compute Units
8

860M Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the Radeon 860M's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The Radeon 860M by AMD dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

Base Clock
600 MHz
Base Clock
600 MHz
Boost Clock
3000 MHz
Boost Clock
3,000 MHz
Memory Clock
System Shared
GDDR GDDR 6X 6X

AMD's Radeon 860M Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Radeon 860M's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.

Memory Size
System Shared
Memory Type
System Shared
VRAM Type
System Shared
Memory Bus
System Shared
Bandwidth
System Dependent

Radeon 860M by AMD Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the 860M, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.

L1 Cache
128 KB per Array
L2 Cache
1024 KB

860M Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the AMD Radeon 860M against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.

FP32 (Float)
3.072 TFLOPS
FP64 (Double)
192.0 GFLOPS (1:16)
FP16 (Half)
3.072 TFLOPS (1:1)
Pixel Rate
48.00 GPixel/s
Texture Rate
96.00 GTexel/s

Radeon 860M Ray Tracing & AI

Hardware acceleration features

The AMD Radeon 860M includes dedicated hardware for ray tracing and AI acceleration. RT cores handle real-time ray tracing calculations for realistic lighting, reflections, and shadows in supported games. Tensor cores (NVIDIA) or XMX cores (Intel) accelerate AI workloads including DLSS, FSR, and XeSS upscaling technologies. These features enable higher visual quality without proportional performance costs, making the 860M capable of delivering both stunning graphics and smooth frame rates in modern titles.

RT Cores
8

RDNA 3.5 Architecture & Process

Manufacturing and design details

The AMD Radeon 860M is built on AMD's RDNA 3.5 architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the 860M will perform in GPU benchmarks compared to previous generations.

Architecture
RDNA 3.5
GPU Name
Krackan Point
Process Node
4 nm
Foundry
TSMC
Transistors
unknown
Die Size
unknown

Power & Thermal

TDP and power requirements

Power specifications for the AMD Radeon 860M determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the Radeon 860M to maintain boost clocks without throttling.

TDP
15 W
TDP
15W
Power Connectors
None

Radeon 860M by AMD Physical & Connectivity

Dimensions and outputs

Physical dimensions of the AMD Radeon 860M are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.

Slot Width
IGP
Bus Interface
PCIe 4.0 x8
Display Outputs
Portable Device Dependent
Display Outputs
Portable Device Dependent

AMD API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the AMD Radeon 860M. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.

DirectX
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenGL
4.6
Vulkan
1.4
Vulkan
1.4
OpenCL
2.1
Shader Model
6.8

Radeon 860M Product Information

Release and pricing details

The AMD Radeon 860M is manufactured by AMD as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the Radeon 860M by AMD represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.

Manufacturer
AMD
Release Date
Mar 2025
Production
Active
Predecessor
Navi II IGP

About AMD Radeon 860M

The AMD Radeon 860M, built on the 4 nm process at TSMC using the RDNA 3.5 architecture and the Krackan Point chip, posts an average benchmark score of 26401, placing it at the 70th percentile of all GPUs. This integrated graphics processor (IGP) from the Navi III IGP generation delivers performance that lands squarely between dedicated desktop cards from several generations ago, making it a surprisingly potent option for thin-and-light systems. The data shows a GPU that trades blows with discrete solutions, with its nearest rival, the AMD Radeon RX 5700 XT 50th Anniversary, matching its average score almost exactly at 26403.

Benchmark Performance

The core metric from the benchmark data is the average score of 26401, which is derived from two specific tests: 22759 in Geekbench OpenCL and a notably stronger 30043 in Geekbench Vulkan. This discrepancy suggests the architecture's strengths are more fully realized through the Vulkan API, which is common for modern RDNA-based designs. When positioned against its nearest rivals, the 860M's performance is remarkably consistent. It sits a mere 0% delta from the AMD Radeon RX 5700 XT 50th Anniversary, meaning the integrated chip effectively matches that older desktop card's output in these synthetic workloads.

Further analysis shows a 1.1% advantage over the AMD Radeon R9 M290X, a mobile discrete GPU from a previous era, and a 2% lead over the AMD Radeon R9 370X. While these deltas are small, they are consistent, indicating the 860M does not just compete with, but slightly edges out, these older discrete parts. The only rival it trails is the NVIDIA RTX A4000, which sits 1.2% ahead. This is a professional workstation card, so the margin is contextually significant; the 860M is within striking distance of a much more expensive and power-hungry component. The near-parity with the RX 5700 XT 50th Anniversary is the headline result here, as it demonstrates that modern integrated graphics have closed the gap with mid-range desktop hardware from roughly five years ago, at least in compute-centric benchmarks.

Memory Subsystem

The memory configuration for the Radeon 860M is entirely system-dependent. It uses "System Shared" memory for its size, type, and bus width, meaning it has no dedicated VRAM of its own. Consequently, the bandwidth is also listed as "System Dependent," which is a critical caveat for performance. The GPU will rely on the laptop's main system memory (typically DDR5 or LPDDR5) for all frame buffer operations, and the speed and channel configuration of that system RAM will directly dictate the available bandwidth.

For high-resolution gaming, this presents a significant bottleneck. While the compute performance (3.072 TFLOPS FP32) is sufficient to drive modern games at 1080p, the lack of dedicated high-bandwidth memory means that performance at 1440p or 4K will likely degrade more sharply than it would on a discrete GPU with its own VRAM. The IGP's 8 ROPs and 32 TMUs are also limited, with a pixel rate of 24.00 GPixel/s and a texture rate of 96.00 GTexel/s. These figures, while adequate for 1080p, will struggle to fill a 4K frame buffer, especially when combined with the shared memory bandwidth. The data suggests that the 860M is best positioned as a 1080p performer, where the shared memory bandwidth is less likely to throttle the GPU's compute capabilities.

Ray Tracing and Feature Set

The Radeon 860M includes 8 dedicated ray tracing cores, marking its place in the RDNA 3.5 generation with hardware-accelerated ray tracing capabilities. While the raw RT core count is modest, its presence means the GPU can handle ray-traced effects, albeit likely at reduced resolutions or with lower quality settings compared to its rasterized performance. The API support confirms its modern feature set: it supports DirectX 12 Ultimate (12_2), which is the baseline for current and upcoming AAA titles, alongside OpenGL 4.6 and Vulkan 1.4.

This combination of hardware and API support ensures broad compatibility with all modern game releases. The Vulkan 1.4 support is particularly relevant, as the benchmark data shows a significant performance uplift in the Vulkan test (30043) compared to OpenCL (22759), suggesting that titles leveraging Vulkan will see better frame rates than those using older or more generic compute APIs. The inclusion of ray tracing cores, even in limited number, distinguishes this IGP from older integrated solutions and positions it as a viable option for playing games with some level of RT enabled, provided the resolution and settings are tuned appropriately.

Power and Cooling

Operating at a 15 W TDP, the Radeon 860M is an extraordinarily efficient part. This low power envelope means it requires no external power connectors, as indicated by the "None" field for its power connectors. The slot width is listed as "IGP," which confirms it is designed to be soldered directly onto a motherboard, not installed in a PCIe slot. The bus interface is PCIe 4.0 x8, which provides ample bandwidth for an integrated solution that shares system memory.

The thermal implications are straightforward: a 15 W GPU is far easier to cool than a discrete card. This allows system manufacturers to design thinner and lighter laptops without the need for elaborate cooling solutions or large heatsinks. There is no suggested PSU listed in the data, which is logical given that the GPU draws its power from the motherboard's power delivery system, not a separate PSU. The lack of a dedicated power connector and the minimal power draw are the defining characteristics here, enabling the 860M to be a high-performance IGP in a power-constrained environment.

How It Compares

AMD Radeon RX 5700 XT 50th Anniversary: The most direct comparison shows a 0% delta in average benchmark score (26401 vs 26403). This indicates that the integrated 860M matches the performance of this desktop GPU, which is a remarkable feat given the differences in power consumption and physical size. The 860M essentially replicates the compute performance of this older flagship in synthetic tests.

AMD Radeon R9 M290X: The 860M holds a 1.1% advantage over this mobile discrete GPU. The R9 M290X was a high-end laptop part in its day, and the fact that an IGP can outperform it by a slight margin shows the generational leap in integrated graphics. This delta, while small, is a clear win for the 860M.

NVIDIA RTX A4000: This is the only rival ahead of the 860M, with a 1.2% higher average score (26714 vs 26401). The RTX A4000 is a professional workstation card with much higher power requirements and a dedicated memory bus. The 860M's near-parity with this card, despite the massive differences in design goals, underscores the efficiency and capability of the RDNA 3.5 architecture.

AMD Radeon R9 370X: The 860M leads this desktop card by 2%. The R9 370X was a mid-range desktop GPU, and the 860M's clear, albeit modest, victory over it demonstrates that modern integrated solutions have surpassed the performance of older discrete desktop parts, making them viable for entry-level gaming.

Who Should Consider It

The benchmark data positions the Radeon 860M squarely at 1080p gaming. Given its compute scores, which rival the RX 5700 XT 50th Anniversary, it can handle most modern titles at 1080p with medium to high settings. Users should avoid targeting 1440p or 4K resolutions, as the system-shared memory architecture and limited ROP count (8) will create a severe bottleneck, leading to sub-optimal frame rates. The strong Vulkan performance (30043) suggests that gamers playing Vulkan-based titles will have a better experience than those playing DirectX 12 games, though both are supported via the 12 Ultimate API.

This is a chip for users who need a single, power-efficient solution for light gaming and general productivity. The 15 W TDP means it is ideal for ultraportable laptops where battery life is paramount, but where the user still wants the flexibility to play games at 1080p on the go. It is not a high-refresh-rate or high-resolution gaming part, but as a jack-of-all-trades IGP, the data shows it punches far above its weight class, delivering discrete-class performance in an integrated package.

FAQ

Q: How does the AMD Radeon 860M perform compared to the AMD Radeon RX 5700 XT 50th Anniversary?

A: The benchmark data shows a 0% delta in average scores, with the 860M scoring 26401 and the RX 5700 XT 50th Anniversary scoring 26403, indicating essentially identical performance.

Q: What is the TDP of the Radeon 860M and what are its power requirements?

A: The TDP is 15 W, and it requires no external power connectors, drawing all its power from the motherboard as an IGP.

Q: Does the Radeon 860M support hardware ray tracing?

A: Yes, it includes 8 dedicated ray tracing cores, providing hardware support for ray-traced effects, though performance will be limited by its overall compute power.

Q: What is the memory bandwidth of the Radeon 860M?

A: The memory bandwidth is listed as "System Dependent" because the GPU uses System Shared memory for its VRAM, making performance reliant on the laptop's system RAM configuration.

Q: What APIs are supported by the Radeon 860M?

A: It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the average benchmark score of the Radeon 860M and what percentile does it fall into?

A: The average benchmark score is 26401, which places it in the 70th percentile of all GPUs.

Detailed benchmark scores and charts for the AMD Radeon 860M are below.

Benchmark Scores

geekbench_openclSource

Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how AMD Radeon 860M handles parallel computing tasks like video encoding and scientific simulations. OpenCL is widely supported across different GPU vendors and platforms.

geekbench_opencl #300 of 650
22,759
6%
Max: 388,405
Compare with other GPUs

Top 5 Performers

#1 NVIDIA RTX 6000D
388,405
#2 NVIDIA B300 SXM6 AC
369,831
#3 NVIDIA B200
345,482
#4 NVIDIA H200 NVL
334,891

geekbench_vulkanSource

Geekbench Vulkan tests GPU compute using the modern low-overhead Vulkan API. This shows how AMD Radeon 860M performs with next-generation graphics and compute workloads. Vulkan offers better CPU efficiency than older APIs like OpenGL. Modern games and applications increasingly use Vulkan for cross-platform GPU acceleration.

geekbench_vulkan #245 of 446
30,043
8%
Max: 376,915
Compare with other GPUs

The NVIDIA Equivalent of Radeon 860M

Looking for a similar graphics card from NVIDIA? The NVIDIA GeForce RTX 5070 Ti Mobile offers comparable performance and features in the NVIDIA lineup.

NVIDIA GeForce RTX 5070 Ti Mobile

NVIDIA • 12 GB VRAM

View Specs Compare

Popular AMD Radeon 860M Comparisons

See how the Radeon 860M stacks up against similar graphics cards from the same generation and competing brands.

Compare with Other GPUs

Select another GPU to compare specifications and benchmarks side-by-side.

Browse GPUs