AMD Radeon 860M vs AMD Radeon RX 6600 LE Comparison

Where Each One Wins

The benchmark data splits cleanly along a single axis: the AMD Radeon RX 6600 LE wins every recorded comparison. Out of two head-to-head tests, the discrete card takes both, leaving the AMD Radeon 860M with zero wins. The OpenCL test shows the RX 6600 LE scoring 69,229 against the 860M’s 22,759, a 67.1% advantage. The Vulkan test narrows that gap slightly but still favors the discrete card decisively: 72,428 versus 30,043, a 58.5% lead.

The RX 6600 LE also holds a stronger position in the overall database percentile ranking. It sits at the 91st percentile of all GPUs, while the 860M sits at the 72nd. Its average benchmark score of 70,829 nearly triples the 860M’s average of 26,401. For compute-bound workloads, particularly those that scale with raw shading throughput and dedicated memory bandwidth, the RX 6600 LE is the clear pick. The 860M, by contrast, positions itself as an integrated solution for portable devices, where its 15 W power envelope and system-shared memory are acceptable trade-offs.

Architecture Differences

The two GPUs come from different RDNA generations. The 860M uses RDNA 3.5 on a 4 nm TSMC process, while the RX 6600 LE uses RDNA 2.0 on a 7 nm TSMC process. The 860M is part of the Navi III IGP generation (Strix Point Mobile), built around the Krackan Point chip. The RX 6600 LE belongs to the Radeon RX 6000 series, using the Navi 23 chip and the Navi II generation.

The transistor counts reflect the different design goals. The RX 6600 LE carries 11,060 million transistors on a 237 mm² die, with a density of 46.7M per mm². The 860M’s transistor count and die size are listed as unknown, but its process node advantage (4 nm versus 7 nm) suggests a denser, more power-efficient layout. The 860M’s base clock is 600 MHz with a boost of 3000 MHz; the RX 6600 LE runs a base of 1626 MHz, a boost of 2495 MHz, and a game clock of 2045 MHz.

Compute resources differ substantially. The RX 6600 LE has 1,792 shading units, 112 texture mapping units, 64 ROPs, and 28 ray tracing cores. The 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 RT cores. This 3.5x difference in shading units and 4x difference in ROPs explains the large performance gap. The RX 6600 LE also has a dedicated 8 GB GDDR6 memory pool on a 128-bit bus with 224.0 GB/s bandwidth. The 860M relies on system-shared memory, with bandwidth listed as system dependent.

The RX 6600 LE’s FP32 throughput is 8.942 TFLOPS, nearly three times the 860M’s 3.072 TFLOPS. FP16 performance shows a different ratio: the RX 6600 LE achieves 17.88 TFLOPS (2:1 ratio), while the 860M manages 3.072 TFLOPS (1:1 ratio). The RX 6600 LE also has higher pixel and texture rates: 159.7 GPixel/s and 279.4 GTexel/s versus 48.00 GPixel/s and 96.00 GTexel/s for the 860M.

Head-to-Head Benchmarks

The two recorded benchmarks are Geekbench OpenCL and Geekbench Vulkan. Both use compute workloads that stress the GPU’s raw execution resources. In OpenCL, the RX 6600 LE scores 69,229, which is 67.1% higher than the 860M’s 22,759. In Vulkan, the RX 6600 LE scores 72,428, which is 58.5% higher than the 860M’s 30,043. The Vulkan gap is smaller in percentage terms, but the absolute difference is larger: 42,385 points versus 46,470 points in OpenCL.

The RX 6600 LE’s nearest rivals provide context for its scores. Its average score of 70,829 sits 1% above the NVIDIA RTX A3000 Mobile (70,140), 1.2% above the NVIDIA Quadro P6000 (69,986), and 1.4% above the AMD Radeon Pro WX 8200 (69,870). It trails the AMD Radeon RX 6650M by 1.3% (71,768). These deltas are small, indicating the RX 6600 LE performs in a tight band around its class.

The 860M’s nearest rivals show it clustered with different hardware. Its average of 26,401 is 0.1% below the NVIDIA GeForce MX550 (26,421), 0.3% above the NVIDIA GeForce RTX 5060 (26,331), 0.6% below the AMD Radeon RX 5700 XT 50th Anniversary (26,553), and 1.1% below the NVIDIA RTX A4000 (26,683). These are all sub-2% deltas, meaning the 860M’s performance is competitive with those parts, but all of them sit far below the RX 6600 LE’s tier.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6600 LE has an average score of 70,829, while the AMD Radeon 860M averages 26,401.

Q: How much faster is the RX 6600 LE in the Vulkan benchmark?

A: The RX 6600 LE scores 72,428 versus the 860M’s 30,043, a 58.5% advantage.

Q: What is the memory configuration difference?

A: The RX 6600 LE has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The 860M uses system-shared memory with system-dependent bandwidth.

Q: Do both GPUs support the same DirectX version?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What are the power requirements?

A: The 860M has a 15 W TDP with no power connectors. The RX 6600 LE has a 132 W TDP, requires one 8-pin connector, and a suggested 300 W PSU.

Q: Which GPU has more shading units?

A: The RX 6600 LE has 1,792 shading units, compared to the 860M’s 512.

Specification Differences

The two parts differ in nearly every hardware category. The 860M uses a 4 nm process; the RX 6600 LE uses 7 nm. The 860M has a base clock of 600 MHz and boost of 3000 MHz; the RX 6600 LE has a base of 1626 MHz, boost of 2495 MHz, and game clock of 2045 MHz. Memory differs completely: the 860M uses system-shared memory, while the RX 6600 LE has 8 GB of GDDR6 at 1750 MHz (14 Gbps effective) on a 128-bit bus with 224.0 GB/s bandwidth.

Compute resources: the 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 RT cores. The RX 6600 LE has 1,792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores. Pixel rate: 48.00 GPixel/s versus 159.7 GPixel/s. Texture rate: 96.00 GTexel/s versus 279.4 GTexel/s. FP32: 3.072 TFLOPS versus 8.942 TFLOPS. FP16: 3.072 TFLOPS (1:1) versus 17.88 TFLOPS (2:1).

Power and physical design: the 860M is an IGP with 15 W TDP and no power connectors; the RX 6600 LE is a dual-slot card with 132 W TDP, one 8-pin connector, and a 300 W suggested PSU. The RX 6600 LE measures 190 mm in length, 110 mm in height, and 40 mm in width. The 860M’s dimensions are not recorded. Display outputs: the RX 6600 LE has 1x HDMI 2.1 and 3x DisplayPort 1.4a; the 860M’s outputs are portable device dependent. Both use PCIe 4.0 x8.

Transistor data is only available for the RX 6600 LE: 11,060 million transistors on a 237 mm² die with 46.7M per mm² density. The 860M’s transistor count and die size are unknown. The RX 6600 LE also has a listed predecessor (Navi) and successor (Navi III), while the 860M’s predecessor is Navi II IGP. Release dates differ: the 860M launched February 28, 2025, and the RX 6600 LE launched December 7, 2023.

The Verdict

The data supports a straightforward choice for compute-heavy workloads: the AMD Radeon RX 6600 LE outperforms the AMD Radeon 860M in every recorded benchmark. Its average score is 168% higher, its percentile rank is 19 points higher, and it wins both head-to-head tests by wide margins. The RX 6600 LE’s dedicated 8 GB GDDR6 memory and 224.0 GB/s bandwidth remove the system-memory bottleneck that limits the 860M. Its higher shading unit count, ROP count, and FP32 throughput make it the appropriate pick for tasks that scale with raw compute.

The 860M, however, is not without a role. Its 15 W TDP and IGP form factor suit portable devices where space and power are constrained. Its 4 nm process node and 3000 MHz boost clock indicate a design focused on efficiency within a tight envelope. For integrated graphics, it delivers competitive scores within its class, matching the NVIDIA GeForce MX550 within 0.1% and exceeding the NVIDIA GeForce RTX 5060 by 0.3% on average.

The verdict depends on the use case. For a desktop system with room for a dual-slot card and a 300 W PSU, the RX 6600 LE is the stronger performer by a large margin. For a thin-and-light portable device where a discrete card is not an option, the 860M provides a usable level of graphics performance at a fraction of the power draw. The benchmark database records no scenario where the 860M wins, so the RX 6600 LE is the default choice whenever its power and physical requirements can be met.