Skip to content
RU

GeForce RTX 5080 vs GeForce RTX 5090: specs and benchmark comparison

ANVIDIA · Blackwell

NVIDIA GeForce RTX 5080

  • 16 GB GDDR7
  • 360 W
  • PSU 850 W+

January 30, 2025 · $999 at launch

BNVIDIA · Blackwell

NVIDIA GeForce RTX 5090

  • 32 GB GDDR7
  • 575 W
  • PSU 1000 W+

January 30, 2025 · $1,999 at launch

Short verdict

NVIDIA GeForce RTX 5090 leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.

Compare with AI
← GeForce RTX 5080GeForce RTX 5090 →

  • Rendering and compute

    B +76.7%

    NVIDIA GeForce RTX 5090 leads in this scenario (up to 76.7% 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 GeForce RTX 5080 is better2

  • Board power 215 W lower360 W (TGP) vs 575 W (TGP)

  • Launch price $1,000 lower$999 vs $1,999

Where GeForce RTX 5090 is better4

  • Blender Benchmark 4.5.0 63.9% faster14,978 samples/min vs 9,136 samples/min

  • Shader units 11,008 more21,760 (CUDA cores) vs 10,752 (CUDA cores)

  • Video memory 16 GB more32 GB vs 16 GB

  • Memory bus 256 bit more512 bit vs 256 bit

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

    B ahead by 63.9%

    Position among tested models (67, OptiX)

    A · 9,136B · 14,978
    05,00010,00015,000
    Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min.

    NVIDIA GeForce RTX 5090 is ahead by 63.9% in this benchmark.

    About the measurement and source
    A · NVIDIA GeForce RTX 5080

    9,136.2 samples/min · community measurement, sample 1283 · November 14, 2026

    Blender Open Data (Blender Foundation)

    Median of 1283 submissions (149 outliers excluded), interquartile range 8939.24–9287.65; submissions 2025-07-17 to 2026-10-18; OPTIX backend. Snapshot 2026-11-14.

    B · NVIDIA GeForce RTX 5090

    14,978.4 samples/min · community measurement, sample 1334 · November 14, 2026

    Blender Open Data (Blender Foundation)

    Median of 1334 submissions (221 outliers excluded), interquartile range 14677.66–15255.56; submissions 2025-07-17 to 2026-10-15; OPTIX 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 (6)
BenchmarkABDifference
Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,329.216,330.8B +75%
Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,162.916,189.8B +76.7%
Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,022.614,904.4B +65.2%
Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,162.815,097.9B +64.8%
Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)8,708.414,411.8B +65.5%
Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,432.616,312.9B +72.9%

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

Reference results (8)
BenchmarkABDifference
Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA)6,112.3—no pair
Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (CUDA)4,953.1—no pair
Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)8,870.714,263.3reference
Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)10,583.217,822.2reference
Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,070.2—no pair
Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)9,004.8—no pair
Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal)10,09519,417.5reference
Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA)—10,016.4no pair

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

Specifications

Chip

  • Architecture

    ABlackwell

    BBlackwell

    equal

  • Shader units

    A10,752 (CUDA cores)

    B21,760 (CUDA cores)

    B: 11,008 more

    Shader unit counts are comparable only within one architecture.

Clocks

  • Base clock

    A2,300 MHz

    B2,010 MHz

    A: 290 MHz more

  • Boost clock

    A2,620 MHz

    B2,410 MHz

    A: 210 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

    A16 GB

    B32 GB

    B: 16 GB more

  • Memory type

    AGDDR7

    BGDDR7

    equal

  • Memory bus

    A256 bit

    B512 bit

    B: 256 bit more

Power and dimensions

  • Board power

    A360 W (TGP)

    B575 W (TGP)

    B: 215 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

    A850 W

    B1,000 W

    B: 150 W higher

  • Interface

    APCIe 5.0

    BPCIe 5.0

    equal

  • Length (reference / Founders Edition)

    A304 mm

    B304 mm

    equal

    Partner cards have different dimensions; check the specific SKU.

  • Thickness (slots)

    A2

    B2

    equal

  • Power connectors (reference)

    A1x 16-pin (adapter to 3x 8-pin included) — Founders Edition

    B4x 8-pin (adapter) or 1x 600 W PCIe Gen 5 — FE

    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.

AI verdict

Questions and answers

How much video memory do NVIDIA GeForce RTX 5080 and NVIDIA GeForce RTX 5090 have?

NVIDIA GeForce RTX 5080: 16 GB GDDR7, 256-bit bus. NVIDIA GeForce RTX 5090: 32 GB GDDR7, 512-bit bus.

What power supply does the manufacturer recommend?

For NVIDIA GeForce RTX 5080, 850 W or more; for NVIDIA GeForce RTX 5090, 1000 W or more. This is a recommendation for a typical system; also check the power connectors of the specific card model.

Which PCIe interface do the cards use?

NVIDIA GeForce RTX 5080: PCIe 5.0. NVIDIA GeForce RTX 5090: PCIe 5.0.

Which is faster: NVIDIA GeForce RTX 5080 or NVIDIA GeForce RTX 5090?

NVIDIA GeForce RTX 5090 leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.

Data sources (3)
  • NVIDIA — specifications of NVIDIA GeForce RTX 5080, specifications of NVIDIA GeForce RTX 5090checked November 7, 2026
  • Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 5.2.0, 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 5.3.0checked November 14, 2026
  • Wikipedia (English) — release date and launch pricechecked November 14, 2026

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

TelegramVK