GeForce RTX 3090 Ti vs GeForce RTX 4080 Laptop GPU: specs and benchmark comparison
ANVIDIA · Ampere
NVIDIA GeForce RTX 3090 Ti
- 24 GB GDDR6X
- 450 W
- PSU 850 W+
March 29, 2022 · $1,999 at launch
Short verdict
NVIDIA GeForce RTX 3090 Ti leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.
Compare with AIRendering and compute
A +11.7%NVIDIA GeForce RTX 3090 Ti leads in this scenario (up to 11.7% 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 3090 Ti is better2
Video memory 12 GB more24 GB vs 12 GB
Memory bus 192 bit more384 bit vs 192 bit
Where GeForce RTX 4080 Laptop GPU is better0
No advantages found in our data.
Benchmarks
Results are compared within one benchmark, one version and the same conditions. Laptop chip results depend on the laptop model: its maker sets the power limit and cooling.
- 3.2% difference, within the threshold
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 3090 Ti5,611.6 samples/minGeForce RTX 4080 Laptop GPU5,435 samples/minPosition among tested models (67, OptiX)
B · 5,435A · 5,61205,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. The 3.2% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 3090 Ti
5,611.6 samples/min · community measurement, sample 133 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 133 submissions (6 outliers excluded), interquartile range 5039.69–5780.09; submissions 2025-07-17 to 2026-03-01; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 4080 Laptop GPU
5,435 samples/min · community measurement, sample 85 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 85 submissions (2 outliers excluded), interquartile range 4717.6–5590.65; submissions 2025-07-17 to 2026-10-19; 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 (8)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,774.1 | 5,341.5 | A +8.1% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,514.9 | 6,273.3 | A +3.8% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,644.1 | 6,300.4 | A +5.5% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,585.8 | 6,371.2 | A +3.4% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,383.1 | 5,630.9 | B +4.6% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,853.8 | 5,242.4 | A +11.7% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,629.2 | 5,117 | A +10% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,695.1 | 5,383.8 | A +5.8% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (13)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 4,094.2 | — | no pair |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 4,561.8 | 3,994.3 | reference |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,472.1 | 4,773.1 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,264 | 4,928.2 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,865.7 | — | no pair |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,992.8 | — | no pair |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,865.5 | — | no pair |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,112.3 | — | no pair |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,067.1 | 5,375.8 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,298.2 | 5,715.5 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 4,823.7 | 5,329.3 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 4,572.9 | 5,524.5 | reference |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 6,253.4 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
Chip maker values. The laptop maker sets the power limit and clocks in each laptop.
| Specification | A · GeForce RTX 3090 Ti | B · GeForce RTX 4080 Laptop GPU | Difference |
|---|---|---|---|
| Chip | |||
| Architecture | Ampere | Ada Lovelace | differs |
| Shader unitsShader unit counts are comparable only within one architecture. | 10,752 (CUDA cores) | 7,424 (CUDA cores) | not directly comparable |
| Clocks | |||
| Base clock | 1,560 MHz | no data | no data for B |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,860 MHz | 1,350–2,280 MHz | not directly comparable |
| Memory | |||
| Video memory | 24 GB | 12 GB | A: 12 GB more |
| Memory type | GDDR6X | GDDR6 | differs |
| Memory bus | 384 bit | 192 bit | A: 192 bit more |
| 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. | 450 W (board power) | 60–150 W (graphics subsystem power) | not directly comparable |
| Recommended PSU | 850 W | no data | no data for B |
| Interface | no data | PCIe 4.0 | no data for A |
| Length (reference / Founders Edition)Partner cards have different dimensions; check the specific SKU. | 313 mm | no data | no data for B |
| Thickness (slots) | 3 | no data | no data for B |
| Power connectors (reference) | 3x 8-pin (adapter) or 450+ W PCIe Gen 5 — FE | no data | no data for B |
Chip
Architecture
AAmpere
BAda Lovelace
differsShader units
A10,752 (CUDA cores)
B7,424 (CUDA cores)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,560 MHz
Bno data
no data for BBoost clock
A1,860 MHz
B1,350–2,280 MHz
not directly comparableClocks 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
B12 GB
A: 12 GB moreMemory type
AGDDR6X
BGDDR6
differsMemory bus
A384 bit
B192 bit
A: 192 bit more
Power and dimensions
Board power
A450 W (board power)
B60–150 W (graphics subsystem power)
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
A850 W
Bno data
no data for BInterface
Ano data
BPCIe 4.0
no data for ALength (reference / Founders Edition)
A313 mm
Bno data
no data for BPartner cards have different dimensions; check the specific SKU.
Thickness (slots)
A3
Bno data
no data for BPower connectors (reference)
A3x 8-pin (adapter) or 450+ W PCIe Gen 5 — FE
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.
Questions and answers
How much video memory do NVIDIA GeForce RTX 3090 Ti and NVIDIA GeForce RTX 4080 Laptop GPU have?
NVIDIA GeForce RTX 3090 Ti: 24 GB GDDR6X, 384-bit bus. NVIDIA GeForce RTX 4080 Laptop GPU: 12 GB GDDR6, 192-bit bus.
Which is faster: NVIDIA GeForce RTX 3090 Ti or NVIDIA GeForce RTX 4080 Laptop GPU?
NVIDIA GeForce RTX 3090 Ti leads in every scenario with comparable benchmarks: rendering and compute. This does not imply an advantage in tasks without benchmarks.
See also
Data sources (3)
- NVIDIA — specifications of NVIDIA GeForce RTX 3090 Ti, specifications of NVIDIA GeForce RTX 4080 Laptop GPUchecked November 7, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 3.4.0, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 3.1.0, benchmark Blender Benchmark 3.1.2, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 3.2.1, benchmark Blender Benchmark 3.3.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.1.0, 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 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.