AMD Radeon RX 470 vs NVIDIA GeForce GTX 1630 Comparison

The Verdict

The AMD Radeon RX 470 and NVIDIA GeForce GTX 1630 are both end-of-life graphics cards, but they target entirely different performance strata. The database records an average benchmark score of 28,996 for the RX 470 versus 24,277 for the GTX 1630, a gap of roughly 19 percent in favor of the older AMD part. In direct head-to-head testing, the RX 470 wins both recorded workloads, with a 35 percent lead in Geekbench OpenCL and a 68.3 percent lead in Geekbench Vulkan. The GTX 1630's only advantage is physical: it is a single-slot, 145 mm card with no auxiliary power connector, whereas the RX 470 is a dual-slot, 240 mm board requiring a 6-pin connector. The data suggests that anyone needing maximum compute performance from a legacy card should choose the RX 470, while those constrained by space or power delivery may find the GTX 1630 acceptable despite its lower scores. The RX 470 also holds a higher percentile rank among all GPUs (74th versus 70th), reinforcing its superior standing in the database's aggregate metrics.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon RX 470 records an average benchmark score of 28,996, while the NVIDIA GeForce GTX 1630 scores 24,277. The RX 470's nearest rivals include the AMD Radeon RX 6800M (28,874, a 0.4 percent difference) and the Intel Arc A370M (29,175, a -0.6 percent difference). The GTX 1630 sits near the NVIDIA GeForce GTX 780 Ti (24,236, a 0.2 percent difference) and the AMD Radeon RX 6600 XT (24,442, a -0.7 percent difference).

Q: How do the two cards compare in Vulkan performance?

A: In the Geekbench Vulkan test, the RX 470 scores 39,884 versus the GTX 1630's 23,695, a 68.3 percent advantage for the AMD card. This is the largest recorded performance delta between the two in any workload.

Q: Does the GTX 1630 have a smaller physical footprint?

A: Yes. The GTX 1630 measures 145 mm in length, 69 mm in height, and 18 mm in width, and it occupies a single slot. The RX 470 measures 240 mm in length, 95 mm in height, and 35 mm in width, requiring a dual-slot design.

Q: What are the power requirements for each card?

A: The RX 470 has a TDP of 120 W and requires a 6-pin power connector, with a suggested power supply of 300 W. The GTX 1630 has a TDP of 75 W, uses no power connectors, and carries a suggested power supply of 250 W.

Q: Which card supports a newer DirectX feature level?

A: The GTX 1630 supports DirectX 12 (12_1), while the RX 470 supports DirectX 12 (12_0). Both cards support OpenGL 4.6, but the GTX 1630 supports Vulkan 1.4 versus Vulkan 1.3 on the RX 470.

Q: Are there any benchmark tests where the GTX 1630 wins?

A: No. In the head-to-head benchmark results, the RX 470 wins both recorded tests (Geekbench OpenCL and Geekbench Vulkan). The win tally is 2 for the RX 470 and 0 for the GTX 1630.

Architecture Differences

The RX 470 is built on AMD's GCN 4.0 architecture, using the Ellesmere chip produced on a 14 nm process at GlobalFoundries. The GTX 1630 employs NVIDIA's Turing architecture, specifically the TU117 chip, fabricated on a 12 nm process at TSMC. These are fundamentally different designs: GCN 4.0 is a compute-oriented architecture from the Arctic Islands generation (RX 400 series), while Turing is a graphics-focused architecture from the GeForce 16 series. The RX 470 integrates 5,700 million transistors on a 232 mm² die, yielding a transistor density of 24.6 million per mm². The GTX 1630 packs 4,700 million transistors into a 200 mm² die, for a density of 23.5 million per mm². Despite being newer and smaller, the GTX 1630 has fewer transistors and a lower density, reflecting its cut-down configuration.

The RX 470's GCN 4.0 design uses 2,048 shading units, 128 texture mapping units, and 32 raster output units. The GTX 1630 has only 512 shading units, 32 TMUs, and 16 ROPs. Neither card includes dedicated ray tracing cores or tensor cores, as the GTX 1630 predates NVIDIA's RTX lineup and the RX 470 predates AMD's ray tracing hardware. The RX 470's compute throughput is substantially higher: it delivers 4.940 TFLOPS of FP32 performance, while the GTX 1630 manages 1.828 TFLOPS. In FP16, the RX 470 maintains a 1:1 ratio at 4.940 TFLOPS, whereas the GTX 1630 achieves 3.656 TFLOPS at a 2:1 ratio, meaning its FP16 throughput is double its FP32 rate.

Memory architecture also diverges sharply. The RX 470 uses 4 GB of GDDR5 on a 256-bit bus, producing 211.2 GB/s of bandwidth. The GTX 1630 uses 4 GB of GDDR6 on a 64-bit bus, yielding only 96.00 GB/s. The effective memory clock differs as well: the RX 470 runs at 6.6 Gbps effective, while the GTX 1630 runs at 12 Gbps effective. The narrower bus on the GTX 1630 negates the faster memory speed, resulting in less than half the bandwidth of the RX 470.

API support shows a split. The GTX 1630 supports DirectX 12 (12_1), a higher feature level than the RX 470's 12_0, and also supports Vulkan 1.4 versus Vulkan 1.3 on the RX 470. Both cards support OpenGL 4.6. The RX 470's display outputs include one HDMI 2.0b and three DisplayPort 1.4a connections, while the GTX 1630 offers one DVI, one HDMI 2.0, and one DisplayPort 1.4a. The RX 470 therefore provides more modern display connectivity out of the box.

Specification Differences

The recorded specifications differ across nearly every major category. The process node is 14 nm for the RX 470 and 12 nm for the GTX 1630. The RX 470 uses the Ellesmere chip, while the GTX 1630 uses TU117. Transistor counts are 5,700 million versus 4,700 million, and die sizes are 232 mm² versus 200 mm². Transistor density stands at 24.6M per mm² for the RX 470 and 23.5M per mm² for the GTX 1630.

Clock speeds show a significant inversion. The RX 470's base clock is 926 MHz with a boost of 1206 MHz. The GTX 1630's base clock is 1740 MHz with a boost of 1785 MHz. The GTX 1630 runs at much higher frequencies, but its smaller shader count means it still trails in raw throughput. Memory clocks also differ: 1650 MHz (6.6 Gbps effective) on the RX 470 versus 1500 MHz (12 Gbps effective) on the GTX 1630.

Memory bus width is 256 bit on the RX 470 versus 64 bit on the GTX 1630. Bandwidth is 211.2 GB/s versus 96.00 GB/s. Shading units are 2,048 versus 512, TMUs are 128 versus 32, and ROPs are 32 versus 16. Pixel rate is 38.59 GPixel/s on the RX 470 versus 28.56 GPixel/s on the GTX 1630. Texture rate is 154.4 GTexel/s versus 57.12 GTexel/s. FP32 performance is 4.940 TFLOPS versus 1.828 TFLOPS, and FP16 is 4.940 TFLOPS (1:1) versus 3.656 TFLOPS (2:1).

Power and physical specifications heavily favor the GTX 1630. TDP is 120 W versus 75 W. The RX 470 requires a dual-slot cooler and a 6-pin power connector, while the GTX 1630 is single-slot with no power connectors. Suggested PSU is 300 W for the RX 470 versus 250 W for the GTX 1630. The RX 470 is 240 mm long, 95 mm tall, and 35 mm wide; the GTX 1630 is 145 mm long, 69 mm tall, and 18 mm wide. The RX 470's launch MSRP was 179 USD; the GTX 1630 has no recorded launch MSRP.

Release dates differ by nearly six years: the RX 470 launched on 2016-08-03, while the GTX 1630 launched on 2022-06-27. Both are end-of-life. The RX 470's predecessor is Pirate Islands and its successor is Polaris. The GTX 1630's predecessor is GeForce 10 and its successor is GeForce 20.

Head-to-Head Benchmarks

The database records two direct head-to-head benchmark comparisons between the RX 470 and the GTX 1630. In both, the RX 470 emerges victorious, and the margins are substantial.

The first test is Geekbench OpenCL. The RX 470 scores 33,568, while the GTX 1630 scores 24,858. This gives the RX 470 a 35 percent advantage. This result aligns with the raw compute specifications: the RX 470's 4.940 TFLOPS of FP32 performance is more than 2.7 times the GTX 1630's 1.828 TFLOPS. The RX 470's wider 256-bit memory bus and 211.2 GB/s bandwidth also help feed its 2,048 shading units, whereas the GTX 1630's 64-bit bus and 96.00 GB/s bandwidth constrain its 512 shading units. The OpenCL score difference is notable but not as extreme as the Vulkan gap.

The second test is Geekbench Vulkan, where the RX 470 scores 39,884 versus 23,695 for the GTX 1630. This is a 68.3 percent lead for the AMD card, the largest margin in any recorded comparison. The RX 470's Vulkan score is also higher than its own OpenCL score, suggesting strong driver optimization for the Vulkan API on GCN 4.0. The GTX 1630's Vulkan score is slightly lower than its OpenCL score, indicating a relative weakness in Vulkan workloads despite supporting Vulkan 1.4, a newer API version than the RX 470's Vulkan 1.3. The delta of 16,189 points between the two cards in Vulkan is more than double the delta of 8,710 points in OpenCL.

The win tally stands at 2 wins for the RX 470 and 0 for the GTX 1630. This outcome is consistent with the aggregate data: the RX 470's average benchmark score of 28,996 places it in the 74th percentile of all GPUs, while the GTX 1630's 24,277 sits in the 70th percentile. The RX 470's nearest rival in the database is the AMD Radeon RX 6800M, with an average score of 28,874 and a delta of 0.4 percent, meaning the RX 470 is effectively tied with a mobile flagship from a later generation. The GTX 1630's nearest rival is the NVIDIA GeForce GTX 780 Ti, with an average score of 24,236 and a delta of 0.2 percent, placing it in the company of a high-end card from 2013.

The performance picture is unambiguous: the RX 470 dominates the GTX 1630 in every recorded benchmark, often by wide margins. The GTX 1630's only redeeming qualities are its compact size, low 75 W TDP, lack of power connectors, and newer DirectX feature level. For anyone prioritizing compute or gaming performance, the RX 470 is the clear choice based on the data. For compact builds with limited power delivery, the GTX 1630 may fit where the RX 470 cannot, but it accepts a significant performance penalty to do so.