GeForce RTX 4080 SUPER vs Radeon RX 7900 XTX: specs and benchmark comparison
ANVIDIA · Ada Lovelace
NVIDIA GeForce RTX 4080 SUPER
- 16 GB GDDR6X
- 320 W
- PSU 750 W+
January 31, 2024 · $999 at launch
Short verdict
Not enough data for a performance conclusion: the database has no comparable benchmarks for this pair. Below are the key differences in official specifications.
Compare with AIAdvantages
Only measured and rated values: a noticeable benchmark gap and specs where more is better.
Where GeForce RTX 4080 SUPER is better0
No advantages found in our data.
Where Radeon RX 7900 XTX is better1
Video memory 8 GB more24 GB vs 16 GB
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 4080 SUPER8,430.2 samples/minRadeon RX 7900 XTX4,340.7 samples/minNo advantage conclusion: different render backends: OptiX and HIP; the difference depends on the software stack, not only on the graphics card.
About the measurement and source
- A · NVIDIA GeForce RTX 4080 SUPER
8,430.2 samples/min · community measurement, sample 233 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 233 submissions (6 outliers excluded), interquartile range 8071.61–8656.32; submissions 2025-07-16 to 2026-10-15; OPTIX backend. Snapshot 2026-11-14.
- B · AMD Radeon RX 7900 XTX
4,340.7 samples/min · community measurement, sample 218 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 218 submissions (3 outliers excluded), interquartile range 4096.83–4501.39; submissions 2025-07-18 to 2026-09-26; HIP backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Cycles render in Blender Benchmark. Median of the sum of samples per minute over three scenes after removing outliers.
Reference results (18)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 4,526.5 | — | no pair |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 5,675.3 | — | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 5,702.1 | — | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,364.3 | 4,199.9 | reference |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,383.2 | 4,914.2 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,225.4 | 4,987.1 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,945.6 | — | no pair |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 9,448.4 | — | no pair |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 9,503.1 | 3,620.8 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 9,904.9 | 3,690.6 | reference |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 9,533.8 | 3,970.6 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,521.5 | 3,931 | reference |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,715.1 | 4,097.5 | reference |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,363.6 | 4,245.5 | reference |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,473.5 | 4,369.7 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,622.3 | 3,940.1 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 8,589.7 | 4,642.3 | reference |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 9,573.1 | 4,566.1 | reference |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce RTX 4080 SUPER | B · Radeon RX 7900 XTX | Difference |
|---|---|---|---|
| Chip | |||
| Architecture | Ada Lovelace | RDNA 3 | differs |
| Compute unitsSM (NVIDIA), CU (AMD) and Xe-core (Intel) are different units and are not compared numerically across vendors. | no data | 96 CU | no data for A |
| Shader unitsShader unit counts are comparable only within one architecture. | 10,240 (CUDA cores) | 6,144 (Stream processors) | not directly comparable |
| Clocks | |||
| Base clock | 2,290 MHz | no data | no data for B |
| Game Clock (AMD) | no data | 2,300 MHz | no data for A |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 2,550 MHz | 2,500 MHz | A: 50 MHz more |
| Memory | |||
| Video memory | 16 GB | 24 GB | B: 8 GB more |
| Memory type | GDDR6X | GDDR6 | differs |
| Memory bus | 256 bit | no data | no data for B |
| Memory speed | no data | 20 Gbps | no data for A |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | no data | 960 GB/s | no data for A |
| Power and dimensions | |||
| Board powerTGP (NVIDIA) and TBP (AMD/Intel) are calculated differently; higher is not better. For laptops, the chip maker sets the range and the laptop maker picks the value, so the same chip behaves differently in different laptops. | 320 W (TGP) | 355 W (TBP) | not directly comparable |
| Recommended PSU | 750 W | 800 W | B: 50 W higher |
| Length (reference / Founders Edition)Partner cards have different dimensions; check the specific SKU. | 304 mm | 287 mm | A: 17 mm higher |
| Thickness (slots) | 3 | 2.5 | A: 0.5 higher |
| Power connectors (reference) | 3x 8-pin (adapter) or 450+ W PCIe Gen 5 — FE | 2x 8-pin (reference card) | differs |
Chip
Architecture
AAda Lovelace
BRDNA 3
differsCompute units
Ano data
B96 CU
no data for ASM (NVIDIA), CU (AMD) and Xe-core (Intel) are different units and are not compared numerically across vendors.
Shader units
A10,240 (CUDA cores)
B6,144 (Stream processors)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A2,290 MHz
Bno data
no data for BGame Clock (AMD)
Ano data
B2,300 MHz
no data for ABoost clock
A2,550 MHz
B2,500 MHz
A: 50 MHz moreClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit.
Memory
Video memory
A16 GB
B24 GB
B: 8 GB moreMemory type
AGDDR6X
BGDDR6
differsMemory bus
A256 bit
Bno data
no data for BMemory speed
Ano data
B20 Gbps
no data for AMemory bandwidth
Ano data
B960 GB/s
no data for AExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A320 W (TGP)
B355 W (TBP)
not directly comparableTGP (NVIDIA) and TBP (AMD/Intel) are calculated differently; higher is not better. For laptops, the chip maker sets the range and the laptop maker picks the value, so the same chip behaves differently in different laptops.
Recommended PSU
A750 W
B800 W
B: 50 W higherLength (reference / Founders Edition)
A304 mm
B287 mm
A: 17 mm higherPartner cards have different dimensions; check the specific SKU.
Thickness (slots)
A3
B2.5
A: 0.5 higherPower connectors (reference)
A3x 8-pin (adapter) or 450+ W PCIe Gen 5 — FE
B2x 8-pin (reference card)
differs
“More” does not always mean “better”: higher power draw or size is a system requirement, not an advantage (such bars are dimmed).
Compare with AI
An AI model reviews the specs and benchmarks of this pair and gives a plain-language verdict on who each model suits.
Questions and answers
How much video memory do NVIDIA GeForce RTX 4080 SUPER and AMD Radeon RX 7900 XTX have?
NVIDIA GeForce RTX 4080 SUPER: 16 GB GDDR6X, 256-bit bus. AMD Radeon RX 7900 XTX: 24 GB GDDR6.
What power supply does the manufacturer recommend?
For NVIDIA GeForce RTX 4080 SUPER, 750 W or more; for AMD Radeon RX 7900 XTX, 800 W or more. This is a recommendation for a typical system; also check the power connectors of the specific card model.
See also
Data sources (4)
- NVIDIA — specifications of NVIDIA GeForce RTX 4080 SUPERchecked November 7, 2026
- AMD — specifications of AMD Radeon RX 7900 XTXchecked November 7, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.4.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 5.0.0, benchmark Blender Benchmark 5.1.0, benchmark Blender Benchmark 5.3.0, benchmark Blender Benchmark 3.2.1, benchmark Blender Benchmark 3.3.0checked November 14, 2026
- Wikipedia (English) — release date and launch pricechecked November 14, 2026
How we compare: methodology. Where the data comes from: sources.