AMD Radeon 860M vs AMD Steam Machine GPU Comparison

FAQ

Q: How does the AMD Radeon 860M compare to the AMD Steam Machine GPU in raw compute performance?

A: The Steam Machine GPU delivers 17.56 TFLOPS of FP32 compute, while the Radeon 860M delivers 3.072 TFLOPS. This represents a 5.7x advantage for the Steam Machine GPU in peak floating-point throughput.

Q: What are the memory specifications of each GPU?

A: The Radeon 860M uses System Shared memory with bandwidth that is System Dependent, meaning it relies on the host platform's memory subsystem. The Steam Machine GPU has 8 GB of dedicated GDDR6 memory on a 128-bit bus with 288.0 GB/s bandwidth.

Q: Which GPU has a higher benchmark percentile ranking?

A: The Radeon 860M ranks in the 72nd percentile among all GPUs in the database, while the Steam Machine GPU ranks in the 50th percentile. The Radeon 860M has recorded benchmark scores, whereas the Steam Machine GPU has no recorded benchmark entries.

Q: What are the architectural differences between the two chips?

A: The Radeon 860M uses RDNA 3.5 architecture on a 4 nm process from TSMC, while the Steam Machine GPU uses RDNA 3.0 architecture on a 6 nm process. The Steam Machine GPU has a discrete chip (Navi 33) with 13,300 million transistors on a 204 mm² die, while the Radeon 860M's transistor count and die size are unknown.

Q: How do the clock speeds differ?

A: The Radeon 860M has a base clock of 600 MHz and a boost clock of 3000 MHz. The Steam Machine GPU has a base clock of 1720 MHz, a boost clock of 2450 MHz, and a game clock of 2250 MHz. The Radeon 860M has a higher peak boost clock, but the Steam Machine GPU operates at much higher base and sustained game clocks.

Q: What is the power consumption difference?

A: The Radeon 860M has a TDP of 15 W and is an integrated graphics processor (IGP). The Steam Machine GPU has a TDP of 110 W and is a discrete console GPU. The Steam Machine GPU consumes over 7x the power of the Radeon 860M.

Architecture Differences

The two GPUs represent fundamentally different design philosophies within AMD's RDNA family. The Radeon 860M is an integrated graphics processor built on the Krackan Point chip, using the newer RDNA 3.5 architecture on TSMC's 4 nm process. It belongs to the Navi III IGP generation for Strix Point Mobile platforms and is designed to share system memory. The Steam Machine GPU, by contrast, is a discrete console GPU using the Navi 33 chip with RDNA 3.0 architecture on a 6 nm process, carrying the codename Hotpink Bonefish and belonging to the Console GPU generation for Valve.

The Steam Machine GPU is a much larger chip: it contains 13,300 million transistors on a 204 mm² die, with a transistor density of 65.2M per mm². The Radeon 860M's transistor count and die size are not recorded in the database. The process node difference, 4 nm versus 6 nm, gives the Radeon 860M a manufacturing advantage, but the Steam Machine GPU compensates with far more silicon resources.

The shading engine configurations differ substantially. The Radeon 860M has 512 shading units, 32 texture mapping units, 16 render output units, and 8 ray tracing cores. The Steam Machine GPU has 1792 shading units, 112 TMUs, 64 ROPs, and 28 ray tracing cores. This is a 3.5x difference in shading units, a 3.5x difference in TMUs, a 4x difference in ROPs, and a 3.5x difference in ray tracing cores, all favoring the discrete console GPU.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature parity is maintained. Neither has tensor cores recorded. The Radeon 860M uses a PCIe 4.0 x8 bus interface, while the Steam Machine GPU's bus interface is not recorded. The Steam Machine GPU has dedicated display outputs (1x HDMI 2.1a and 1x DisplayPort 2.1), whereas the Radeon 860M's display outputs are portable device dependent.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between the AMD Radeon 860M and the AMD Steam Machine GPU. The head-to-head benchmark array is empty, and the win counts for both GPUs are zero. However, indirect comparisons are possible through the Radeon 860M's recorded benchmarks and the Steam Machine GPU's architectural specifications.

The Radeon 860M has two recorded benchmark scores. In Geekbench OpenCL, it scores 22759. In Geekbench Vulkan, it scores 30043. Its average benchmark score is 26401, which places it in the 72nd percentile of all GPUs in the database. The Steam Machine GPU has no recorded benchmarks and an average benchmark score of zero, placing it in the 50th percentile by default.

The Radeon 860M's nearest rivals in the database provide context for its performance level. Its average score of 26401 is nearly identical to the NVIDIA GeForce MX550 at 26421, a delta of -0.1%. It is 0.3% ahead of the NVIDIA GeForce RTX 5060 at 26331, 0.6% behind the AMD Radeon RX 5700 XT 50th Anniversary at 26553, and 1.1% behind the NVIDIA RTX A4000 at 26683. These small deltas indicate that the Radeon 860M performs in a tight band alongside these discrete GPUs from previous generations.

The Steam Machine GPU's FP32 throughput of 17.56 TFLOPS is 5.7x higher than the Radeon 860M's 3.072 TFLOPS. Its pixel rate of 156.8 GPixel/s is 3.3x the Radeon 860M's 48.00 GPixel/s. Its texture rate of 274.4 GTexel/s is 2.9x the Radeon 860M's 96.00 GTexel/s. These theoretical peak rates suggest a substantial performance advantage for the Steam Machine GPU in workloads that scale with raw throughput, though without recorded benchmarks for the Steam Machine GPU, actual measured performance remains unverified.

Specification Differences

The two GPUs differ across nearly every recorded specification field.

Process and Die: The Radeon 860M is fabricated on a 4 nm process by TSMC, while the Steam Machine GPU uses a 6 nm process, also from TSMC. The Steam Machine GPU's die size is 204 mm² with 13,300 million transistors and a density of 65.2M per mm². The Radeon 860M's transistor count and die size are unknown.

Clocks: The Radeon 860M has a base clock of 600 MHz and a boost clock of 3000 MHz. The Steam Machine GPU has a base clock of 1720 MHz, a boost clock of 2450 MHz, and a game clock of 2250 MHz. The Steam Machine GPU also has a memory clock of 2250 MHz (18 Gbps effective), while the Radeon 860M's memory clock is System Shared.

Memory: The Radeon 860M uses System Shared memory with System Dependent bandwidth. The Steam Machine GPU has 8 GB of GDDR6 memory on a 128-bit bus with 288.0 GB/s bandwidth.

Compute Units: The Radeon 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 RT cores. The Steam Machine GPU has 1792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores.

Rates and Throughput: The Radeon 860M achieves 48.00 GPixel/s pixel rate and 96.00 GTexel/s texture rate, with 3.072 TFLOPS FP32 and FP16 (1:1). The Steam Machine GPU achieves 156.8 GPixel/s and 274.4 GTexel/s, with 17.56 TFLOPS FP32 and FP16 (1:1).

Power: The Radeon 860M has a TDP of 15 W and is an IGP with no power connectors. The Steam Machine GPU has a TDP of 110 W and also has no power connectors recorded, but it is a discrete console GPU.

Physical and Interface: The Radeon 860M uses PCIe 4.0 x8 and has no recorded dimensions. The Steam Machine GPU has dimensions of 156 mm by 152 mm by 162 mm and its bus interface is not recorded.

Release Date: The Radeon 860M was released on 2025-02-28, while the Steam Machine GPU has a release date of 2026-06-28.

Where Each One Wins

The Radeon 860M wins in efficiency and portability. Its 15 W TDP makes it suitable for mobile platforms where power is constrained. Its 4 nm process node is more advanced than the Steam Machine GPU's 6 nm node. Its boost clock of 3000 MHz is higher than the Steam Machine GPU's 2450 MHz boost, which can benefit single-threaded or lightly threaded workloads that scale with clock frequency. The Radeon 860M also has recorded benchmark scores, placing it in the 72nd percentile, and its nearest rival comparisons show it competes with discrete mobile and desktop GPUs from NVIDIA and AMD. It supports PCIe 4.0 x8, providing a modern host interface.

The Steam Machine GPU wins in raw compute and memory bandwidth. Its 17.56 TFLOPS FP32 throughput is 5.7x higher than the Radeon 860M. Its 288.0 GB/s dedicated memory bandwidth is a decisive advantage over the Radeon 860M's system-dependent shared memory, which can be a bottleneck in memory-intensive workloads. The Steam Machine GPU's 8 GB GDDR6 memory is dedicated, eliminating contention with the CPU for memory access. Its 28 ray tracing cores versus 8 provide significantly higher ray tracing throughput. The Steam Machine GPU's 156.8 GPixel/s pixel rate and 274.4 GTexel/s texture rate indicate much higher fill rates, which benefit high-resolution rendering and texture-heavy scenes. Its 1792 shading units and 112 TMUs provide the parallel execution resources needed for complex shader workloads.

The Steam Machine GPU also wins on sustained clock performance. Its game clock of 2250 MHz represents a realistic sustained frequency during gaming workloads, whereas the Radeon 860M's 3000 MHz boost is a peak value that may not be sustainable given its IGP thermal constraints. The Steam Machine GPU's 110 W TDP allows for continuous operation at high clocks without the thermal throttling that a 15 W IGP might experience.

The Verdict

The data indicates that the AMD Steam Machine GPU is designed for a fundamentally different performance class than the AMD Radeon 860M. With 5.7x the FP32 throughput, 3.3x the pixel rate, and 2.9x the texture rate, the Steam Machine GPU holds decisive advantages in every raw performance metric recorded. Its dedicated 8 GB GDDR6 memory with 288.0 GB/s bandwidth eliminates the shared-memory bottleneck that constrains the Radeon 860M. The Steam Machine GPU's 110 W TDP, while much higher, enables sustained operation at game clocks that the Radeon 860M cannot match.

The Radeon 860M, however, is not without justification. Its 15 W TDP makes it appropriate for power-constrained mobile devices where a discrete GPU is not feasible. Its 4 nm process node represents a more advanced manufacturing technology. Its 72nd percentile ranking, supported by actual benchmark scores of 22759 in Geekbench OpenCL and 30043 in Geekbench Vulkan, confirms that it delivers competitive performance for its class, matching discrete GPUs like the NVIDIA GeForce MX550 within 0.1% and the NVIDIA GeForce RTX 5060 within 0.3%.

For users requiring maximum graphics throughput, high-resolution rendering, or ray tracing performance, the Steam Machine GPU is the clear choice based on its architectural resources. For users prioritizing power efficiency, portability, and integration into a mobile platform, the Radeon 860M offers a compelling balance. The Steam Machine GPU's lack of recorded benchmarks means its real-world performance is not yet verified in the database, while the Radeon 860M's measured scores provide concrete evidence of its capabilities. The Radeon 860M is the safer choice for verified performance, but the Steam Machine GPU's theoretical specifications suggest it operates in a substantially higher performance tier.