AMD Radeon RX 7650 GRE vs NVIDIA Jetson Orin Nano Super Comparison

AMD
RADEON

AMD Radeon RX 7650 GRE

CORE STATE Navi 33
VRAM 8 GB
CLOCK SPEED 2695 MHz
TDP 170 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 3.0
nm
PROCESS 6 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

Jetson Orin Nano Super

CORE STATE GA10B
VRAM 8 GB
CLOCK SPEED —
TDP 25 W
BUS WIDTH 128 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,336
N/A
geekbench_opencl
83,109
N/A

Analysis: AMD Radeon RX 7650 GRE vs NVIDIA Jetson Orin Nano Super

# Where Each One Wins

The AMD Radeon RX 7650 GRE and NVIDIA Jetson Orin Nano Super occupy entirely different performance strata, and the recorded data reflects that separation clearly. The Radeon RX 7650 GRE carries a benchmark percentile of 83 among all GPUs, placing it comfortably in the upper tier of the database. The Jetson Orin Nano Super sits at the 50th percentile, a median position that indicates substantially lower raw graphics throughput. The RX 7650 GRE delivers 22.08 TFLOPS of FP32 compute, while the Jetson Orin Nano Super delivers 2.089 TFLOPS, a difference of roughly 10.6 times in favor of the AMD part.

In terms of measured benchmark results, the RX 7650 GRE records an average benchmark score of 42,723 across the database. Its nearest rivals include the NVIDIA GeForce RTX 4070 SUPER at 43,223 (delta of -1.2%), the NVIDIA Quadro M6000 24 GB at 43,262 (delta of -1.2%), the NVIDIA GeForce RTX 5050 Mobile at 43,268 (delta of -1.3%), and the NVIDIA Quadro M6000 at 43,301 (delta of -1.3%). These deltas indicate that the RX 7650 GRE sits within a narrow band of less than 1.5% of these competing parts, making it effectively comparable in aggregate performance to those higher-tier products despite its lower placement in the product stack.

The Jetson Orin Nano Super has no recorded benchmark scores and no nearest rivals in the database. Its average benchmark score is listed as zero, which reflects the absence of collected data rather than a literal performance result. The database shows no head-to-head benchmark entries and zero wins for either product in direct comparison. This absence of comparative data means the performance relationship must be established through the architectural and specification differences recorded for each unit.

The use-case split is therefore clear. The RX 7650 GRE is positioned for conventional desktop graphics workloads, with a dual-slot form factor, a 170 W TDP, and a 450 W suggested power supply. The Jetson Orin Nano Super is an integrated graphics processor (IGP) intended for embedded and edge applications, with a 25 W TDP, no power connector requirements, and dimensions of 70 mm by 45 mm. The RX 7650 GRE targets scenarios where sustained high frame rates and heavy rasterization matter, while the Jetson Orin Nano Super targets power-constrained deployments where the 25 W envelope and compact footprint take priority.

# Architecture Differences

The architectural divide between these two products is fundamental. The RX 7650 GRE uses the Navi 33 chip built on RDNA 3.0 architecture, with the codename Hotpink Bonefish, and belongs to the Navi III (RX 7000) generation. The Jetson Orin Nano Super uses the GA10B chip built on Ampere architecture and belongs to the Tegra (Ampere) generation. The process nodes differ: TSMC fabricates the AMD part at 6 nm, while Samsung fabricates the NVIDIA part at 8 nm.

Transistor counts and die sizes show a contrast in design philosophy. The RX 7650 GRE contains 13,300 million transistors on a 204 mm² die, yielding a transistor density of 65.2 million per square millimeter. The Jetson Orin Nano Super lists its transistor count as unknown but occupies a 200 mm² die with no recorded density figure. The close die sizes with vastly different transistor counts indicate that the AMD chip packs far more logic into a similar physical area, consistent with its higher performance classification.

The compute resources diverge sharply. The RX 7650 GRE uses 2,048 shading units, 128 texture mapping units, 64 render output units, and 32 ray tracing cores. The Jetson Orin Nano Super uses 1,024 shading units, 32 texture mapping units, 16 render output units, and no ray tracing cores. Instead, the NVIDIA part includes 32 tensor cores, which the AMD part lacks entirely. This reflects the different intended workloads: the RX 7650 GRE focuses on traditional graphics pipelines with dedicated ray tracing hardware, while the Jetson Orin Nano Super allocates silicon to tensor processing for AI inference tasks.

Pixel and texture rates reinforce the performance gap. The RX 7650 GRE achieves 172.5 GPixel/s and 345.0 GTexel/s, while the Jetson Orin Nano Super achieves 16.32 GPixel/s and 32.64 GTexel/s. The FP16 capabilities also differ in ratio: the RX 7650 GRE delivers 22.08 TFLOPS of FP16 with a 1:1 ratio to FP32, while the Jetson Orin Nano Super delivers 4.178 TFLOPS of FP16 with a 2:1 ratio. The 2:1 ratio on the NVIDIA part indicates that its FP16 throughput is double its FP32 throughput, a characteristic that suits mixed-precision AI workloads, whereas the AMD part treats FP16 and FP32 at the same rate.

# FAQ

Q: What is the performance gap in FP32 compute between the two products?

A: The RX 7650 GRE delivers 22.08 TFLOPS of FP32, while the Jetson Orin Nano Super delivers 2.089 TFLOPS. The AMD part provides approximately 10.6 times the FP32 throughput of the NVIDIA part.

Q: Do both products have the same memory capacity?

A: Yes, both use 8 GB of memory. However, the RX 7650 GRE uses GDDR6 with a 128-bit bus and 288.0 GB/s bandwidth, while the Jetson Orin Nano Super uses LPDDR5 with a 128-bit bus and 102.4 GB/s bandwidth.

Q: Which product includes tensor cores?

A: The Jetson Orin Nano Super includes 32 tensor cores. The RX 7650 GRE has no tensor cores recorded in its specifications.

Q: What are the power requirements for each product?

A: The RX 7650 GRE has a 170 W TDP and requires a 450 W suggested power supply with a single 8-pin connector. The Jetson Orin Nano Super has a 25 W TDP with no power connector listed and no suggested PSU requirement.

Q: How do the benchmark percentiles compare?

A: The RX 7650 GRE sits at the 83rd percentile among all GPUs, while the Jetson Orin Nano Super sits at the 50th percentile. The RX 7650 GRE also has recorded benchmark scores, whereas the Jetson Orin Nano Super has no recorded benchmark scores in the database.

Q: What API support do both products share?

A: Both products support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means they offer identical API feature levels despite their architectural differences.

# Specification Differences

The two products differ across nearly every major specification category. The process node is 6 nm for the RX 7650 GRE and 8 nm for the Jetson Orin Nano Super. The foundry is TSMC for AMD and Samsung for NVIDIA. The RX 7650 GRE has 13,300 million transistors on a 204 mm² die, while the Jetson Orin Nano Super has an unknown transistor count on a 200 mm² die.

Clock speeds show a significant divergence. The RX 7650 GRE has recorded base, boost, and game clocks of 1720 MHz, 2695 MHz, and 2350 MHz respectively. The Jetson Orin Nano Super has no base, boost, or game clock recorded. Memory clocks also differ: the RX 7650 GRE operates at 2250 MHz with 18 Gbps effective, while the Jetson Orin Nano Super operates at 800 MHz with 6.4 Gbps effective.

Memory bandwidth separates the two clearly. The RX 7650 GRE provides 288.0 GB/s, nearly three times the 102.4 GB/s of the Jetson Orin Nano Super. Both use 8 GB capacity and a 128-bit bus, but the memory type differs: GDDR6 for AMD and LPDDR5 for NVIDIA.

Compute unit counts diverge across all categories. The RX 7650 GRE has 2,048 shading units versus 1,024, 128 TMUs versus 32, 64 ROPs versus 16, and 32 ray tracing cores versus none. The Jetson Orin Nano Super has 32 tensor cores while the RX 7650 GRE has none. Pixel rates are 172.5 GPixel/s versus 16.32 GPixel/s, and texture rates are 345.0 GTexel/s versus 32.64 GTexel/s.

Physical specifications separate the products into different classes. The RX 7650 GRE is a dual-slot card measuring 204 mm in length and 115 mm in height. The Jetson Orin Nano Super is an IGP measuring 70 mm by 45 mm. The RX 7650 GRE uses PCIe 4.0 x8 while the Jetson Orin Nano Super uses PCIe 4.0 x4. Display outputs differ as well: the RX 7650 GRE provides 1x HDMI 2.1a and 3x DisplayPort 2.1, while the Jetson Orin Nano Super lists display outputs as portable device dependent.

Release dates and pricing fields also differ. The RX 7650 GRE launched on 2025-02-06 with a launch MSRP of 279 USD. The Jetson Orin Nano Super launched on 2024-12-16 with a launch MSRP of 249 USD. The RX 7650 GRE lists a predecessor of Navi II and a successor of Navi IV, while the Jetson Orin Nano Super lists neither.

# Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between the RX 7650 GRE and the Jetson Orin Nano Super. The wins counter shows zero for both products, and the head-to-head benchmarks array is empty. This absence of direct comparative measurements means the performance relationship must be inferred from the individual benchmark results and specification data recorded for each product.

The RX 7650 GRE has two specific benchmark scores in the database. In 3dmark_3dmark_steel_nomad_dx12, it scores 2,336. In geekbench_opencl, it scores 83,109. These results contribute to its average benchmark score of 42,723 and its 83rd percentile placement among all GPUs. The Jetson Orin Nano Super has no benchmark scores recorded, yielding an average benchmark score of zero and a 50th percentile placement.

The nearest rival data for the RX 7650 GRE provides context for its aggregate performance. The NVIDIA GeForce RTX 4070 SUPER scores 43,223, which is 1.2% above the RX 7650 GRE. The NVIDIA Quadro M6000 24 GB scores 43,262, also 1.2% above. The NVIDIA GeForce RTX 5050 Mobile scores 43,268, 1.3% above, and the NVIDIA Quadro M6000 scores 43,301, 1.3% above. These narrow deltas indicate that the RX 7650 GRE performs within a tight cluster of these established products, despite being positioned lower in its product stack.

The Jetson Orin Nano Super has no nearest rivals listed, reflecting its unique positioning as an embedded IGP rather than a conventional discrete GPU. Its 2.089 TFLOPS FP32 throughput and 16.32 GPixel/s pixel rate place it in a performance tier that the database does not populate with comparable products. Its 102.4 GB/s memory bandwidth, while lower than the RX 7650 GRE, still supports its intended embedded workloads.

The FP16 comparison is instructive for AI-related tasks. The RX 7650 GRE delivers 22.08 TFLOPS of FP16 with a 1:1 ratio, meaning its FP16 performance equals its FP32 performance. The Jetson Orin Nano Super delivers 4.178 TFLOPS of FP16 with a 2:1 ratio, meaning its FP16 performance doubles its FP32 performance. The NVIDIA part's tensor cores combined with its FP16 advantage suggest that its design prioritizes inference workloads, while the AMD part's balanced FP16 and FP32 rates reflect a focus on graphics rendering.

The thermal and power data place the products in different operational envelopes. The RX 7650 GRE operates at 170 W TDP with a 450 W suggested PSU, while the Jetson Orin Nano Super operates at 25 W TDP with no PSU requirement. The 145 W difference in TDP translates directly into the performance gap observed in the specification data, with the AMD part consuming substantially more power to deliver its higher throughput.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 7650 GRE
Jetson Orin Nano Super
Core Specs
Shading Units
2,048
1,024 -50.0%
Shaders
2,048
1,024 -50.0%
TMUs
128
32 -75.0%
ROPs
64
16 -75.0%
Compute Units
32
—
SM Count
—
8
Clocks
Base Clock
1720 MHz
—
Boost Clock
2695 MHz
—
GPU Clock
—
1020 MHz
Game Clock
2350 MHz
—
Shader Clock
2350 MHz
—
Memory Clock
2250 MHz 18 Gbps effective
800 MHz 6.4 Gbps effective
Memory
Memory Size
8 GB
8 GB
VRAM (MB)
8,192
8,192 0.0%
Memory Type
GDDR6
LPDDR5
Memory Bus
128 bit
128 bit
Bandwidth
288.0 GB/s
102.4 GB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
2 MB
2 MB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
172.5 GPixel/s
16.32 GPixel/s
Texture Rate
345.0 GTexel/s
32.64 GTexel/s
FP32 (TFLOPS)
22.08 TFLOPS
2.089 TFLOPS
FP64 (TFLOPS)
689.9 GFLOPS (1:32)
—
FP16 (TFLOPS)
22.08 TFLOPS (1:1)
4.178 TFLOPS (2:1)
AI/RT
RT Cores
32
—
Tensor Cores
—
32
Matrix Cores
64
—
Power
TDP
170 W
25 W
TDP (W)
170
25 -85.3%
Suggested PSU
450 W
—
Power Connectors
1x 8-pin
—
Architecture
Architecture
RDNA 3.0
Ampere
GPU Name
Navi 33
GA10B
Codename
Hotpink Bonefish
—
Generation
Navi III (RX 7000)
Tegra (Ampere)
Process Size
6 nm
8 nm
Transistors
13,300 million
unknown
Die Size
204 mm²
200 mm²
Foundry
TSMC
Samsung
Density
65.2M / mm²
—
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.2
3.0
CUDA
—
8.7
Shader Model
6.9
6.8
Physical
Slot Width
Dual-slot
IGP
Length
204 mm 8 inches
70 mm 2.8 inches
Height
115 mm 4.5 inches
45 mm 1.8 inches
Outputs
1x HDMI 2.1a3x DisplayPort 2.1
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x4
Other
Launch Price
279 USD
249 USD
Production
Active
Active
Predecessor
Navi II
—
Successor
Navi IV
—
View Radeon RX 7650 GRE Details View Jetson Orin Nano Super Details