Skip to content
RU

Radeon RX 7900 XTX vs Radeon RX 9070: specs and benchmark comparison

AAMD · RDNA 3

AMD Radeon RX 7900 XTX

  • 24 GB GDDR6
  • 355 W
  • PSU 800 W+

December 13, 2022 · $999 at launch

BAMD · RDNA 4

AMD Radeon RX 9070

  • 16 GB GDDR6
  • 220 W
  • PSU 650 W+

March 6, 2025 · $549 at launch

Short verdict

AMD Radeon RX 7900 XTX leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.

Compare with AI
← Radeon RX 7900 XTXRadeon RX 9070 →
  • Rendering and compute

    A +66.9%

    AMD Radeon RX 7900 XTX leads in this scenario (up to 66.9% in comparable benchmarks).

No comparable benchmarks yet: gaming: rasterization, gaming: ray tracing, power efficiency.

Advantages

Only measured and rated values: a noticeable benchmark gap and specs where more is better.

Where Radeon RX 7900 XTX is better4

  • Blender Benchmark 4.5.0 53.5% faster4,341 samples/min vs 2,827 samples/min

  • Compute units 40 more96 CU vs 56 CU

  • Video memory 8 GB more24 GB vs 16 GB

  • Memory bandwidth 320 GB/s more960 GB/s vs 640 GB/s

Where Radeon RX 9070 is better2

  • Board power 135 W lower220 W (TBP) vs 355 W (TBP)

  • Launch price $450 lower$549 vs $999

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

    A ahead by 53.5%

    Position among tested models (13, HIP)

    B · 2,827A · 4,341
    02,0004,0006,000
    Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min.

    AMD Radeon RX 7900 XTX is ahead by 53.5% in this benchmark.

    About the measurement and source
    A · 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.

    B · AMD Radeon RX 9070

    2,827 samples/min · community measurement, sample 89 · November 14, 2026

    Blender Open Data (Blender Foundation)

    Median of 89 submissions (1 outliers excluded), interquartile range 2749.55–2964.73; submissions 2025-07-17 to 2026-03-10; 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.

Other comparable benchmarks (2)
BenchmarkABDifference
Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,987.12,987.8A +66.9%
Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,369.72,710.4A +61.2%

Each benchmark version has its own scale: numbers are compared only within a row.

Reference results (11)
BenchmarkABDifference
Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,199.9—no pair
Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,914.23,145.5reference
Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)3,620.8—no pair
Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)3,690.6—no pair
Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)3,970.6—no pair
Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)3,931—no pair
Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,097.5—no pair
Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,245.52,949.1reference
Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)3,940.12,692.9reference
Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,642.33,224.3reference
Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)4,566.1—no pair

Each benchmark version has its own scale: numbers are compared only within a row.

Specifications

Chip

  • Architecture

    ARDNA 3

    BRDNA 4

    differs
  • Compute units

    A96 CU

    B56 CU

    A: 40 more

    SM (NVIDIA), CU (AMD) and Xe-core (Intel) are different units and are not compared numerically across vendors.

  • Shader units

    A6,144 (Stream processors)

    B3,584 (Stream processors)

    not directly comparable

    Shader unit counts are comparable only within one architecture.

Clocks

  • Game Clock (AMD)

    A2,300 MHz

    B2,070 MHz

    A: 230 MHz more
  • Boost clock

    A2,500 MHz

    B2,520 MHz

    B: 20 MHz more

    Clocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit.

Memory

  • Video memory

    A24 GB

    B16 GB

    A: 8 GB more
  • Memory type

    AGDDR6

    BGDDR6

    equal
  • Memory bus

    Ano data

    B256 bit

    no data for A
  • Memory speed

    A20 Gbps

    B20 Gbps

    equal
  • Memory bandwidth

    A960 GB/s

    B640 GB/s

    A: 320 GB/s more

    Excludes cache (Infinity Cache / L2), which affects effective bandwidth differently.

Power and dimensions

  • Board power

    A355 W (TBP)

    B220 W (TBP)

    A: 135 W higher

    TGP (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

    A800 W

    B650 W

    A: 150 W higher
  • Interface

    Ano data

    BPCIe 5.0 x16

    no data for A
  • Length (reference / Founders Edition)

    A287 mm

    Bno data

    no data for B

    Partner cards have different dimensions; check the specific SKU.

  • Thickness (slots)

    A2.5

    Bno data

    no data for B
  • Power connectors (reference)

    A2x 8-pin (reference card)

    Bno data

    no data for B

“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.

AI verdict

Questions and answers

How much video memory do AMD Radeon RX 7900 XTX and AMD Radeon RX 9070 have?

AMD Radeon RX 7900 XTX: 24 GB GDDR6. AMD Radeon RX 9070: 16 GB GDDR6, 256-bit bus.

What power supply does the manufacturer recommend?

For AMD Radeon RX 7900 XTX, 800 W or more; for AMD Radeon RX 9070, 650 W or more. This is a recommendation for a typical system; also check the power connectors of the specific card model.

Which is faster: AMD Radeon RX 7900 XTX or AMD Radeon RX 9070?

AMD Radeon RX 7900 XTX leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.

Data sources (3)
  • AMD — specifications of AMD Radeon RX 7900 XTX, specifications of AMD Radeon RX 9070checked November 7, 2026
  • Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 5.0.0, benchmark Blender Benchmark 5.1.0, benchmark Blender Benchmark 4.2.0, 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 5.3.0checked November 14, 2026
  • Wikipedia (English) — release date and launch pricechecked November 14, 2026

How we compare: methodology. Where the data comes from: sources.

TelegramVK