GeForce RTX 2080 Ti vs GeForce RTX 3070 Laptop GPU: specs and benchmark comparison
Rendering and compute
depends on the taskBenchmark results disagree, so the choice depends on the specific task.
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 2080 Ti is better4
Blender Benchmark 2.93.1 14.2% lower33 s vs 38 s
Blender Benchmark 2.93.1 29% lower63 s vs 82 s
Video memory 3 GB more11 GB vs 8 GB
Memory bus 96 bit more352 bit vs 256 bit
Where GeForce RTX 3070 Laptop GPU is better7
Blender Benchmark 2.93.1 18% lower29 s vs 34 s
Blender Benchmark 2.93.1 28% lower17 s vs 22 s
Blender Benchmark 2.93.1 40.1% lower62 s vs 86 s
Blender Benchmark 2.93.1 16.6% lower178 s vs 208 s
Blender Benchmark 2.93.1 27.4% lower82 s vs 105 s
Blender Benchmark 2.93.1 7.8% lower262 s vs 282 s
Blender Benchmark 2.93.1 13.5% lower122 s vs 138 s
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.
- B ahead by 18%
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce RTX 2080 Ti33.9 sGeForce RTX 3070 Laptop GPU28.7 sPosition among tested models (31, CUDA)
B · 29A · 340100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 18% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
33.9 s · community measurement, sample 53 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 53 submissions (8 outliers excluded), interquartile range 33.42–34.68; submissions 2021-07-15 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
28.7 s · community measurement, sample 116 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 116 submissions (3 outliers excluded), interquartile range 27.25–32.03; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 28%
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
GeForce RTX 2080 Ti22.1 sGeForce RTX 3070 Laptop GPU17.3 sPosition among tested models (20, OptiX)
B · 17A · 22050100150Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 28% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
22.1 s · community measurement, sample 39 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 39 submissions (1 outliers excluded), interquartile range 20.82–22.62; submissions 2021-07-18 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
17.3 s · community measurement, sample 101 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 101 submissions (5 outliers excluded), interquartile range 16.84–19.15; submissions 2021-07-09 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- 2.3% difference, within the threshold
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
GeForce RTX 2080 Ti137.4 sGeForce RTX 3070 Laptop GPU134.3 sPosition among tested models (26, CUDA)
B · 134A · 1370200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 2.3% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
137.4 s · community measurement, sample 45 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 45 submissions (5 outliers excluded), interquartile range 133.31–141.35; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
134.3 s · community measurement, sample 91 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 91 submissions (4 outliers excluded), interquartile range 127.14–146.92; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 40.1%
Blender Benchmark 2.93.1
GPU, classroom (OPTIX) · s, lower is better
GeForce RTX 2080 Ti86.2 sGeForce RTX 3070 Laptop GPU61.5 sPosition among tested models (14, OptiX)
B · 62A · 86050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 40.1% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
86.2 s · community measurement, sample 31 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 31 submissions (3 outliers excluded), interquartile range 83.91–91.02; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
61.5 s · community measurement, sample 87 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 87 submissions (3 outliers excluded), interquartile range 59.14–66.25; submissions 2021-07-09 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- 1.5% difference, within the threshold
Blender Benchmark 2.93.1
GPU, fishy_cat (CUDA) · s, lower is better
GeForce RTX 2080 Ti64.6 sGeForce RTX 3070 Laptop GPU63.7 sPosition among tested models (21, CUDA)
B · 64A · 650100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 1.5% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
64.6 s · community measurement, sample 37 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 37 submissions (7 outliers excluded), interquartile range 63.21–66.02; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
63.7 s · community measurement, sample 70 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 70 submissions (1 outliers excluded), interquartile range 61–70.98; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- A ahead by 14.2%
Blender Benchmark 2.93.1
GPU, fishy_cat (OPTIX) · s, lower is better
GeForce RTX 2080 Ti33.5 sGeForce RTX 3070 Laptop GPU38.2 sPosition among tested models (13, OptiX)
A · 33B · 38020406080Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 2080 Ti is ahead by 14.2% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
33.5 s · community measurement, sample 29 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 29 submissions (2 outliers excluded), interquartile range 32.62–35.12; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
38.2 s · community measurement, sample 73 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 73 submissions (3 outliers excluded), interquartile range 36.93–40.92; submissions 2021-07-09 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- 3% difference, within the threshold
Blender Benchmark 2.93.1
GPU, koro (CUDA) · s, lower is better
GeForce RTX 2080 Ti102.5 sGeForce RTX 3070 Laptop GPU105.5 sPosition among tested models (20, CUDA)
A · 102B · 1060200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. The 3% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
102.5 s · community measurement, sample 36 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 36 submissions (6 outliers excluded), interquartile range 100.68–104.8; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
105.5 s · community measurement, sample 64 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 64 submissions (1 outliers excluded), interquartile range 100.91–115.04; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- A ahead by 29%
Blender Benchmark 2.93.1
GPU, koro (OPTIX) · s, lower is better
GeForce RTX 2080 Ti63.5 sGeForce RTX 3070 Laptop GPU81.9 sPosition among tested models (13, OptiX)
A · 63B · 82050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 2080 Ti is ahead by 29% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
63.5 s · community measurement, sample 24 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 24 submissions (6 outliers excluded), interquartile range 62.26–67.16; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
81.9 s · community measurement, sample 66 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 66 submissions (11 outliers excluded), interquartile range 79.76–87.28; submissions 2021-07-09 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 16.6%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (CUDA) · s, lower is better
GeForce RTX 2080 Ti208.1 sGeForce RTX 3070 Laptop GPU178.5 sPosition among tested models (21, CUDA)
B · 178A · 2080200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 16.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
208.1 s · community measurement, sample 40 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 40 submissions (4 outliers excluded), interquartile range 200.44–213.46; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
178.5 s · community measurement, sample 74 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 74 submissions (2 outliers excluded), interquartile range 169.45–196.61; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 27.4%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (OPTIX) · s, lower is better
GeForce RTX 2080 Ti105.1 sGeForce RTX 3070 Laptop GPU82.5 sPosition among tested models (13, OptiX)
B · 82A · 1050100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 27.4% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
105.1 s · community measurement, sample 38 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 38 submissions (2 outliers excluded), interquartile range 102.5–110.4; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
82.5 s · community measurement, sample 78 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 78 submissions (6 outliers excluded), interquartile range 80.04–88.43; submissions 2021-07-09 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 7.8%
Blender Benchmark 2.93.1
GPU, victor (CUDA) · s, lower is better
GeForce RTX 2080 Ti282 sGeForce RTX 3070 Laptop GPU261.6 sPosition among tested models (19, CUDA)
B · 262A · 28202505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 7.8% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
282 s · community measurement, sample 34 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 34 submissions (7 outliers excluded), interquartile range 274.18–287.61; submissions 2021-07-17 to 2022-02-20; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
261.6 s · community measurement, sample 66 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 66 submissions (1 outliers excluded), interquartile range 249.25–285.23; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- B ahead by 13.5%
Blender Benchmark 2.93.1
GPU, victor (OPTIX) · s, lower is better
GeForce RTX 2080 Ti137.9 sGeForce RTX 3070 Laptop GPU121.5 sPosition among tested models (13, OptiX)
B · 122A · 1380100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3070 Laptop GPU is ahead by 13.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
137.9 s · community measurement, sample 28 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 28 submissions (2 outliers excluded), interquartile range 132.73–144.53; submissions 2021-07-18 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
121.5 s · community measurement, sample 70 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 70 submissions (4 outliers excluded), interquartile range 117.1–128.44; submissions 2021-07-09 to 2022-02-25; OPTIX backend. Snapshot 2026-11-14.
difference = |A − B| ÷ the smaller value × 100%. The 5% noticeable threshold is a UX heuristic, not statistical significance.
Render time of a single Cycles scene without synchronization. Median of submissions after filtering.
- 3.1% 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 2080 Ti2,845.2 samples/minGeForce RTX 3070 Laptop GPU2,760.6 samples/minPosition among tested models (67, OptiX)
B · 2,761A · 2,84505,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. The 3.1% difference is below the noticeable threshold (5%).
About the measurement and source
- A · NVIDIA GeForce RTX 2080 Ti
2,845.2 samples/min · community measurement, sample 131 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 131 submissions (5 outliers excluded), interquartile range 2732.17–2950.36; submissions 2025-07-18 to 2026-03-23; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3070 Laptop GPU
2,760.6 samples/min · community measurement, sample 118 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 118 submissions (5 outliers excluded), interquartile range 2251.76–2939.6; submissions 2025-07-17 to 2026-08-15; 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 (24)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 39.1 | 30.2 | B +29.4% |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 19.8 | 16.5 | B +20.1% |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 159.2 | 99.7 | B +59.7% |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 84.2 | 60.6 | B +38.9% |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 70.9 | 67.4 | B +5.3% |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 33.1 | 38.4 | A +15.7% |
| Blender Benchmark 2.92GPU, koro (CUDA) | 111.1 | 114.7 | A +3.2% |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 98.4 | 122.2 | A +24.2% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 225.1 | 204.6 | B +10.1% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 100.2 | 80.8 | B +24.1% |
| Blender Benchmark 2.92GPU, victor (CUDA) | 330 | 324.6 | B +1.7% |
| Blender Benchmark 2.92GPU, victor (OPTIX) | 137.1 | 123.6 | B +10.9% |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,799.5 | 2,914.8 | B +4.1% |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,835.9 | 2,804.4 | A +1.1% |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,084.5 | 3,003.3 | A +2.7% |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,235.5 | 2,946.5 | A +9.8% |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,223 | 3,287.6 | B +2% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,218.9 | 3,248.3 | B +0.9% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,362.6 | 3,486.4 | B +3.7% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,343.5 | 3,241.2 | A +3.2% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,872.1 | 2,872.2 | B +0% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,903.2 | 3,005.4 | B +3.5% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,818.4 | 2,905.5 | B +3.1% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,792.6 | 2,692.5 | A +3.7% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (91)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81GPU, barbershop_interior (CUDA) | 521.2 | — | no pair |
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 514 | — | no pair |
| Blender Benchmark 2.81GPU, barbershop_interior (OPTIX) | 860.1 | — | no pair |
| Blender Benchmark 2.81aGPU, barbershop_interior (OPTIX) | 866.3 | — | no pair |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 37.5 | — | no pair |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 37.4 | — | no pair |
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 37.7 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 38.2 | — | no pair |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 40.1 | 31.9 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 38.8 | 31.1 | reference |
| Blender Benchmark 2.81GPU, bmw27 (OPTIX) | 19.5 | — | no pair |
| Blender Benchmark 2.81aGPU, bmw27 (OPTIX) | 20.4 | — | no pair |
| Blender Benchmark 2.82GPU, bmw27 (OPTIX) | 20.3 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (OPTIX) | 19.3 | — | no pair |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 19 | 15.6 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 19.3 | 17.8 | reference |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 153.5 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 153.6 | — | no pair |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 147.3 | — | no pair |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 151.1 | — | no pair |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 151.7 | 95.2 | reference |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 154.7 | 102.9 | reference |
| Blender Benchmark 2.81GPU, classroom (OPTIX) | 81.1 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (OPTIX) | 82.6 | — | no pair |
| Blender Benchmark 2.82GPU, classroom (OPTIX) | 81.4 | — | no pair |
| Blender Benchmark 2.83GPU, classroom (OPTIX) | 82.5 | — | no pair |
| Blender Benchmark 2.90GPU, classroom (OPTIX) | 82.1 | 57.4 | reference |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 84.5 | 65.5 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 66.4 | — | no pair |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 67.1 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 68.4 | — | no pair |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 71 | — | no pair |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 72.9 | 62.4 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 67.6 | 61.3 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (OPTIX) | 30.4 | — | no pair |
| Blender Benchmark 2.81aGPU, fishy_cat (OPTIX) | 31.2 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (OPTIX) | 31.9 | — | no pair |
| Blender Benchmark 2.83GPU, fishy_cat (OPTIX) | 31.4 | — | no pair |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | 30.2 | 33.3 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 30.5 | 36.7 | reference |
| Blender Benchmark 2.81GPU, koro (CUDA) | 112.9 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 114.5 | — | no pair |
| Blender Benchmark 2.82GPU, koro (CUDA) | 113.4 | — | no pair |
| Blender Benchmark 2.83GPU, koro (CUDA) | 120.2 | — | no pair |
| Blender Benchmark 2.90GPU, koro (CUDA) | 116.5 | 100.6 | reference |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 108.6 | 105.4 | reference |
| Blender Benchmark 2.81GPU, koro (OPTIX) | 56.1 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (OPTIX) | 55.4 | — | no pair |
| Blender Benchmark 2.82GPU, koro (OPTIX) | 53.5 | — | no pair |
| Blender Benchmark 2.83GPU, koro (OPTIX) | 53.1 | — | no pair |
| Blender Benchmark 2.90GPU, koro (OPTIX) | 59.4 | 74.8 | reference |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 59.2 | 82.6 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 234.9 | — | no pair |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 236.4 | — | no pair |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 234.3 | — | no pair |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 236 | — | no pair |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 242.3 | 181.1 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 223.3 | 190.4 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (OPTIX) | 99.5 | — | no pair |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (OPTIX) | 101.3 | — | no pair |
| Blender Benchmark 2.82GPU, pavillon_barcelona (OPTIX) | 101.6 | — | no pair |
| Blender Benchmark 2.83GPU, pavillon_barcelona (OPTIX) | 99.5 | — | no pair |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | 98 | 76.5 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 99.5 | 86.9 | reference |
| Blender Benchmark 2.81GPU, victor (CUDA) | 288.3 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 290 | — | no pair |
| Blender Benchmark 2.82GPU, victor (CUDA) | 282.3 | — | no pair |
| Blender Benchmark 2.83GPU, victor (CUDA) | 290.2 | — | no pair |
| Blender Benchmark 2.90GPU, victor (CUDA) | 277.9 | 254.4 | reference |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 270.2 | 231.7 | reference |
| Blender Benchmark 2.81GPU, victor (OPTIX) | 131.2 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (OPTIX) | 132.5 | — | no pair |
| Blender Benchmark 2.82GPU, victor (OPTIX) | 129.3 | — | no pair |
| Blender Benchmark 2.83GPU, victor (OPTIX) | 128.9 | — | no pair |
| Blender Benchmark 2.90GPU, victor (OPTIX) | 116.6 | 94.1 | reference |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 118.1 | 104.6 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,112.4 | 1,644.5 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,233.4 | 1,712.4 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,339.9 | 1,667.8 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,461.2 | — | no pair |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,495.4 | 2,168.1 | reference |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,225.7 | — | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,330 | — | no pair |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,754.3 | 2,551.9 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,373.2 | 3,023.2 | reference |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,011.2 | 2,976 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,108.3 | 3,213.5 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,627.7 | 2,685.1 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 2,749.3 | 2,370.4 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,639.8 | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 1,780.2 | 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 2080 Ti | B · GeForce RTX 3070 Laptop GPU | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | TU102-300A-K1-A1 | no data | no data for B |
| Architecture | Turing | Ampere | differs |
| Shader unitsShader unit counts are comparable only within one architecture. | 4,352 (CUDA cores) | 5,120 (CUDA cores) | not directly comparable |
| Clocks | |||
| Base clock | 1,350 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. | 1,545 MHz | 1,290–1,620 MHz | not directly comparable |
| Memory | |||
| Video memory | 11 GB | 8 GB | A: 3 GB more |
| Memory type | GDDR6 | GDDR6 | equal |
| Memory bus | 352 bit | 256 bit | A: 96 bit more |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | 616 GB/s | no data | no data for B |
| 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. | 250 W (TDP) | no data | no data for B |
Chip
GPU chip
ATU102-300A-K1-A1
Bno data
no data for BArchitecture
ATuring
BAmpere
differsShader units
A4,352 (CUDA cores)
B5,120 (CUDA cores)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,350 MHz
Bno data
no data for BBoost clock
A1,545 MHz
B1,290–1,620 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
A11 GB
B8 GB
A: 3 GB moreMemory type
AGDDR6
BGDDR6
equalMemory bus
A352 bit
B256 bit
A: 96 bit moreMemory bandwidth
A616 GB/s
Bno data
no data for BExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A250 W (TDP)
Bno data
no data for BTGP (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.
“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 2080 Ti and NVIDIA GeForce RTX 3070 Laptop GPU have?
NVIDIA GeForce RTX 2080 Ti: 11 GB GDDR6, 352-bit bus. NVIDIA GeForce RTX 3070 Laptop GPU: 8 GB GDDR6, 256-bit bus.
Which is faster: NVIDIA GeForce RTX 2080 Ti or NVIDIA GeForce RTX 3070 Laptop GPU?
It depends on the task: rendering and compute: results disagree.
See also
Data sources (3)
- Wikipedia (English) — specifications of NVIDIA GeForce RTX 2080 Ti, release date and launch pricechecked November 14, 2026
- NVIDIA — specifications of NVIDIA GeForce RTX 3070 Laptop GPUchecked November 7, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 2.81, benchmark Blender Benchmark 2.81a, benchmark Blender Benchmark 2.82, benchmark Blender Benchmark 2.83, benchmark Blender Benchmark 2.90, benchmark Blender Benchmark 2.91.2, benchmark Blender Benchmark 2.92, benchmark Blender Benchmark 2.93.1, benchmark Blender Benchmark 3.1.0, benchmark Blender Benchmark 3.3.0, benchmark Blender Benchmark 3.4.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 3.2.1, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 3.1.2, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 5.0.0, benchmark Blender Benchmark 5.1.0checked November 14, 2026
How we compare: methodology. Where the data comes from: sources.