AMD Radeon R9 M290X vs AMD Radeon RX 6700S Comparison

Launched in January 2014, the AMD Radeon R9 M290X was a high-end mobile GPU for its era, built on the GCN 1.0 architecture with a 28 nm process. The AMD Radeon RX 6700S, arriving in January 2022, is a much more modern part from the RDNA 2.0 generation, built on a 7 nm process. Benchmark data shows the RX 6700S is dramatically faster, delivering roughly triple the performance in both available tests, while the R9 M290X retains a slight percentile ranking edge by a single point. The R9 M290X sits at the 68th percentile of all GPUs, while the RX 6700S sits at the 67th, making their overall standings nearly identical despite the massive performance gap.

The Verdict

The data is unambiguous: the AMD Radeon RX 6700S is the only sensible choice for any modern workload. In Geekbench Metal, the RX 6700S scores 72,864 versus the R9 M290X’s 24,524, a delta of -66.3% in favor of the newer card. In Geekbench OpenCL, the gap is even wider: 70,965 versus 22,028, a -69% delta. The RX 6700S wins both head-to-head tests, giving it a clean 2-0 sweep.

Who should pick the AMD Radeon R9 M290X? Only someone targeting legacy software or a specific 2014-era laptop with an MXM module. Its 4 GB of GDDR5 memory and 153.6 GB/s bandwidth are dwarfed by the RX 6700S’s 8 GB of GDDR6 and 224.0 GB/s bandwidth. The R9 M290X also lacks any ray tracing cores, while the RX 6700S has 28. The older card’s 2.304 TFLOPS FP32 performance is roughly a third of the RX 6700S’s 7.168 TFLOPS.

The RX 6700S is the pick for anyone running current games, creative applications, or compute workloads. Its support for DirectX 12 Ultimate (12_2) versus the R9 M290X’s DirectX 12 (11_1) is a hard generational barrier. The R9 M290X is end-of-life and its successor is listed as Polaris Mobile, which itself has been succeeded by the RX 6700S’s Navi Mobile generation. The data shows the RX 6700S as the only viable option for modern use.

Architecture Differences

The two GPUs share a manufacturer but little else. The R9 M290X uses the Neptune chip on the GCN 1.0 architecture, fabricated by TSMC on a 28 nm process. The RX 6700S uses the Navi 23 chip on RDNA 2.0, also from TSMC but on a 7 nm process. This node shrink allows the RX 6700S to pack 11,060 million transistors into a 237 mm² die, versus the R9 M290X’s 2,800 million transistors on a 212 mm² die. Transistor density improves from 13.2 million per mm² to 46.7 million per mm².

Memory configuration diverges sharply. The R9 M290X has 4 GB of GDDR5 on a 256-bit bus, yielding 153.6 GB/s of bandwidth. The RX 6700S has 8 GB of GDDR6 on a 128-bit bus, yielding 224.0 GB/s. Despite half the bus width, the newer card offers 45% more bandwidth. Clock speeds also reflect the generational leap: the R9 M290X runs at 850 MHz base and 900 MHz boost, while the RX 6700S runs at 1700 MHz base, 1890 MHz game, and 2000 MHz boost.

Compute resources scale accordingly. The R9 M290X has 1,280 shading units, 80 TMUs, and 32 ROPs. The RX 6700S has 1,792 shading units, 112 TMUs, and 64 ROPs. The RX 6700S adds 28 ray tracing cores, a feature entirely absent from the older part. Pixel rate jumps from 28.80 GPixel/s to 128.0 GPixel/s, and texture rate from 72.00 GTexel/s to 224.0 GTexel/s. FP32 throughput more than triples from 2.304 TFLOPS to 7.168 TFLOPS, and the RX 6700S adds FP16 support at 14.34 TFLOPS with a 2:1 ratio.

API support is another clear differentiator. The R9 M290X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The RX 6700S supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The newer card also uses PCIe 4.0 x8, while the older one uses PCIe 3.0 x16. The R9 M290X draws 100 W TDP in an MXM module; the RX 6700S draws 80 W TDP as an IGP, making it both faster and more power-efficient.

FAQ

Q: Which GPU is faster in raw compute performance?

A: The RX 6700S is overwhelmingly faster. It scores 70,965 in Geekbench OpenCL versus the R9 M290X’s 22,028, a 69% difference. Its FP32 output of 7.168 TFLOPS is more than triple the R9 M290X’s 2.304 TFLOPS.

Q: Does the R9 M290X support ray tracing?

A: No. The R9 M290X has no ray tracing cores. The RX 6700S includes 28 ray tracing cores, enabling hardware-accelerated ray tracing.

Q: How do their memory subsystems compare?

A: The R9 M290X has 4 GB of GDDR5 on a 256-bit bus with 153.6 GB/s bandwidth. The RX 6700S has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth, offering more capacity and higher bandwidth.

Q: What is the performance gap in Geekbench Metal?

A: The RX 6700S scores 72,864 versus the R9 M290X’s 24,524, a 66.3% advantage for the newer card.

Q: Which GPU has better API support for modern games?

A: The RX 6700S supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the R9 M290X only supports DirectX 12 (11_1) and Vulkan 1.2.170. The newer card has full support for the latest graphics features.

Q: Are both GPUs still in production?

A: No. Both are listed as end-of-life. The R9 M290X’s successor is Polaris Mobile, and the RX 6700S is part of the Navi Mobile (RX 6000M) generation with no listed successor.

Specification Differences

The specification table shows stark contrasts across nearly every field. The R9 M290X uses a 28 nm process; the RX 6700S uses 7 nm. Transistor count goes from 2,800 million to 11,060 million, and density from 13.2M / mm² to 46.7M / mm². Die size grows slightly from 212 mm² to 237 mm².

Clock speeds triple: base goes from 850 MHz to 1700 MHz, boost from 900 MHz to 2000 MHz, and the RX 6700S adds a 1890 MHz game clock. Memory clock jumps from 1200 MHz (4.8 Gbps effective) to 1750 MHz (14 Gbps effective). Memory size doubles from 4 GB to 8 GB, and type changes from GDDR5 to GDDR6. Bus width halves from 256-bit to 128-bit, but bandwidth rises from 153.6 GB/s to 224.0 GB/s.

Shader resources increase: shading units from 1,280 to 1,792, TMUs from 80 to 112, ROPs from 32 to 64. The RX 6700S adds 28 RT cores. Pixel rate jumps from 28.80 GPixel/s to 128.0 GPixel/s, texture rate from 72.00 GTexel/s to 224.0 GTexel/s. FP32 rises from 2.304 TFLOPS to 7.168 TFLOPS, and FP16 appears at 14.34 TFLOPS. TDP drops from 100 W to 80 W. The R9 M290X uses an MXM module; the RX 6700S uses IGP. Bus interface changes from PCIe 3.0 x16 to PCIe 4.0 x8. DirectX support improves from 12 (11_1) to 12 Ultimate (12_2), and Vulkan from 1.2.170 to 1.4.

Head-to-Head Benchmarks

Only two shared benchmark tests exist in the data, and the RX 6700S wins both decisively. In Geekbench Metal, the RX 6700S scores 72,864 against the R9 M290X’s 24,524. That is a -66.3% delta, meaning the newer card is roughly three times faster. In Geekbench OpenCL, the RX 6700S scores 70,965 against 22,028, a -69% delta. The R9 M290X’s average benchmark score is 23,276, while the RX 6700S’s is 22,154, a slight edge for the older card in this aggregate metric.

The RX 6700S also has a much broader benchmark profile, with results in 3DMark Steel Nomad DX12 (1,451), Passmark DirectX 9 (195), DirectX 10 (87), DirectX 11 (134), DirectX 12 (58), G2D (739), G3D (15,066), and GPU Compute (5,990). The R9 M290X has no comparable results in those tests. The RX 6700S’s Geekbench Vulkan score is 76,150, further demonstrating its compute capability. The R9 M290X has no Vulkan benchmark result available.

Nearest rival data puts both cards in similar company. The R9 M290X’s closest rival is the RX 6600M with a delta of 0%, and it edges out the Pro Vega 16 and P106-100 by 0.1%. The RX 6700S’s closest rival is the RX 5700 at -0.1%, with the RTX 5060 Mobile at -1.3% and the RX 7700 XT at -1.7%. These figures place both GPUs in the mid-to-upper tier of the database, but the RX 6700S’s raw scores are in a different league.

Where Each One Wins

The RX 6700S wins every head-to-head benchmark and dominates in raw specifications. Its 7.168 TFLOPS FP32 and 14.34 TFLOPS FP16 make it suitable for modern gaming, content creation, and GPU compute tasks. The 28 RT cores enable hardware ray tracing, a feature the R9 M290X lacks entirely. The 8 GB GDDR6 memory with 224.0 GB/s bandwidth provides ample capacity and speed for current game textures and high-resolution assets. Its DirectX 12 Ultimate and Vulkan 1.4 support ensure compatibility with the latest graphics APIs.

The R9 M290X has no meaningful wins in the data. Its only advantage is the 68th percentile ranking versus the RX 6700S’s 67th, and its slightly higher average benchmark score of 23,276 versus 22,154. These differences are within the margin of noise given its rival deltas of 0% to 0.1%. The R9 M290X’s 256-bit memory bus is wider, but the RX 6700S’s faster GDDR6 more than compensates. Its MXM form factor might suit a niche upgrade path in old laptops, but its end-of-life status and 28 nm process make it obsolete.

For practical use, the RX 6700S is the clear winner. It offers triple the performance in Metal and OpenCL tests, double the memory, higher bandwidth, and full modern API support. The R9 M290X is only relevant for retro computing or benchmarking curiosity. The data shows no scenario where the older card is preferable for a new purchase. The RX 6700S’s lower TDP of 80 W versus 100 W also makes it more suitable for thin-and-light laptops, despite being significantly faster.