GeForce GTX 1070 vs GeForce GTX 1080 Ti: specs and benchmark comparison
Short verdict
NVIDIA GeForce GTX 1080 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
B +90.3%NVIDIA GeForce GTX 1080 Ti leads in this scenario (up to 90.3% 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 GTX 1070 is better2
Board power 100 W lower150 W (TDP) vs 250 W (TDP)
Launch price $320 lower$379 vs $699
Where GeForce GTX 1080 Ti is better14
Blender Benchmark 2.81 86.7% lower530 s vs 989 s
Blender Benchmark 2.93.1 60.5% lower56 s vs 90 s
Blender Benchmark 2.93.1 72.7% lower63 s vs 108 s
Blender Benchmark 2.93.1 84.9% lower172 s vs 318 s
Blender Benchmark 2.90 86.6% lower213 s vs 397 s
Blender Benchmark 2.93.1 70.1% lower124 s vs 211 s
Blender Benchmark 2.93.1 67.4% lower220 s vs 369 s
Blender Benchmark 2.93.1 77.3% lower311 s vs 551 s
Blender Benchmark 2.93.1 63.1% lower521 s vs 850 s
Blender Benchmark 4.5.0 56.9% faster821 samples/min vs 524 samples/min
Shader units 1,664 more3,584 (CUDA cores) vs 1,920 (CUDA cores)
Video memory 3 GB more11 GB vs 8 GB
Memory bus 96 bit more352 bit vs 256 bit
Memory bandwidth 228.1 GB/s more484.4 GB/s vs 256.3 GB/s
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- B ahead by 86.7%
Blender Benchmark 2.81
GPU, barbershop_interior (CUDA) · s, lower is better
GeForce GTX 1070988.7 sGeForce GTX 1080 Ti529.5 sPosition among tested models (4, CUDA)
B · 530A · 98902505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 86.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
988.7 s · community measurement, sample 24 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 24 submissions (2 outliers excluded), interquartile range 974.27–1022.69; submissions 2020-01-09 to 2020-01-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
529.5 s · community measurement, sample 26 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 26 submissions (0 outliers excluded), interquartile range 513.35–551.47; submissions 2020-01-09 to 2020-01-26; 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 60.5%
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce GTX 107090.2 sGeForce GTX 1080 Ti56.2 sPosition among tested models (31, CUDA)
B · 56A · 900100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 60.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
90.2 s · community measurement, sample 83 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 83 submissions (7 outliers excluded), interquartile range 88.16–91.66; submissions 2021-07-11 to 2022-02-28; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
56.2 s · community measurement, sample 76 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 76 submissions (6 outliers excluded), interquartile range 55.4–57.39; submissions 2021-07-11 to 2022-03-01; 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 72.7%
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
GeForce GTX 1070108.3 sGeForce GTX 1080 Ti62.7 sPosition among tested models (20, OptiX)
B · 63A · 108050100150Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 72.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
108.3 s · community measurement, sample 20 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 20 submissions (2 outliers excluded), interquartile range 106.84–111.79; submissions 2021-07-21 to 2022-02-27; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
62.7 s · community measurement, sample 23 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 23 submissions (1 outliers excluded), interquartile range 60.35–64.88; submissions 2021-07-14 to 2022-02-09; 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 84.9%
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
GeForce GTX 1070317.9 sGeForce GTX 1080 Ti172 sPosition among tested models (26, CUDA)
B · 172A · 3180200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 84.9% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
317.9 s · community measurement, sample 54 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 54 submissions (8 outliers excluded), interquartile range 310.1–327.85; submissions 2021-07-09 to 2022-02-24; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
172 s · community measurement, sample 58 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 58 submissions (7 outliers excluded), interquartile range 169.09–175.74; submissions 2021-07-19 to 2022-03-01; 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 86.6%
Blender Benchmark 2.90
GPU, classroom (OPTIX) · s, lower is better
GeForce GTX 1070396.6 sGeForce GTX 1080 Ti212.6 sPosition among tested models (15, OptiX)
B · 213A · 3970100200300400Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 86.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
396.6 s · community measurement, sample 35 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 35 submissions (0 outliers excluded), interquartile range 369.82–412.67; submissions 2020-09-02 to 2021-01-23; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
212.6 s · community measurement, sample 23 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 23 submissions (1 outliers excluded), interquartile range 203.94–221.54; submissions 2020-09-06 to 2022-01-26; 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 70.1%
Blender Benchmark 2.93.1
GPU, fishy_cat (CUDA) · s, lower is better
GeForce GTX 1070211.5 sGeForce GTX 1080 Ti124.3 sPosition among tested models (21, CUDA)
B · 124A · 2110100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 70.1% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
211.5 s · community measurement, sample 40 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 40 submissions (8 outliers excluded), interquartile range 208.23–215.49; submissions 2021-07-12 to 2022-02-24; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
124.3 s · community measurement, sample 46 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 46 submissions (8 outliers excluded), interquartile range 122.73–126.56; submissions 2021-07-21 to 2022-02-24; 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 67.4%
Blender Benchmark 2.93.1
GPU, koro (CUDA) · s, lower is better
GeForce GTX 1070369 sGeForce GTX 1080 Ti220.4 sPosition among tested models (20, CUDA)
B · 220A · 3690200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 67.4% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
369 s · community measurement, sample 40 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 40 submissions (8 outliers excluded), interquartile range 361.19–376.13; submissions 2021-07-12 to 2022-02-24; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
220.4 s · community measurement, sample 41 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 41 submissions (8 outliers excluded), interquartile range 218.9–224.53; submissions 2021-07-21 to 2022-02-24; 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 77.3%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (CUDA) · s, lower is better
GeForce GTX 1070550.6 sGeForce GTX 1080 Ti310.6 sPosition among tested models (21, CUDA)
B · 311A · 5510200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 77.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
550.6 s · community measurement, sample 46 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 46 submissions (4 outliers excluded), interquartile range 539.97–570.38; submissions 2021-07-12 to 2022-02-24; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
310.6 s · community measurement, sample 42 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 42 submissions (10 outliers excluded), interquartile range 308.52–315.53; submissions 2021-07-21 to 2022-02-24; 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 63.1%
Blender Benchmark 2.93.1
GPU, victor (CUDA) · s, lower is better
GeForce GTX 1070850.4 sGeForce GTX 1080 Ti521.3 sPosition among tested models (19, CUDA)
B · 521A · 85002505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1080 Ti is ahead by 63.1% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
850.4 s · community measurement, sample 40 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 40 submissions (7 outliers excluded), interquartile range 837.37–862.42; submissions 2021-07-12 to 2022-02-24; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
521.3 s · community measurement, sample 41 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 41 submissions (8 outliers excluded), interquartile range 514.79–527.59; submissions 2021-07-21 to 2022-02-24; 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 56.9%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce GTX 1070523.6 samples/minGeForce GTX 1080 Ti821.4 samples/minPosition among tested models (67, OptiX)
A · 524B · 82105,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. NVIDIA GeForce GTX 1080 Ti is ahead by 56.9% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1070
523.6 samples/min · community measurement, sample 72 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 72 submissions (6 outliers excluded), interquartile range 509.18–537.94; submissions 2025-07-25 to 2026-03-05; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 1080 Ti
821.4 samples/min · community measurement, sample 57 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 57 submissions (6 outliers excluded), interquartile range 808.6–840.55; submissions 2025-07-18 to 2026-03-07; 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 (49)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 1,012.7 | 532.3 | B +90.3% |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 103.4 | 62.5 | B +65.3% |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 104.1 | 63.2 | B +64.6% |
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 102.9 | 62.2 | B +65.4% |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 105.6 | 64.1 | B +64.7% |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 112.1 | 69.9 | B +60.4% |
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 104.2 | 64.3 | B +62.2% |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 108.5 | 61.2 | B +77.3% |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 351.4 | 189.1 | B +85.9% |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 361.2 | 192.2 | B +87.9% |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 353.4 | 192.3 | B +83.8% |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 363.8 | 194.8 | B +86.7% |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 365.3 | 197.9 | B +84.5% |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 351.7 | 185 | B +90.1% |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 205.9 | 119.6 | B +72.1% |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 208.3 | 121.3 | B +71.7% |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 211.7 | 123.4 | B +71.6% |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 213 | 124.1 | B +71.7% |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 217.2 | 127.4 | B +70.5% |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 208.4 | 119.1 | B +75% |
| Blender Benchmark 2.81GPU, koro (CUDA) | 401.4 | 245.9 | B +63.2% |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 408.8 | 248.4 | B +64.6% |
| Blender Benchmark 2.82GPU, koro (CUDA) | 401 | 245.2 | B +63.6% |
| Blender Benchmark 2.83GPU, koro (CUDA) | 393.7 | 236 | B +66.8% |
| Blender Benchmark 2.90GPU, koro (CUDA) | 359.7 | 216.7 | B +66% |
| Blender Benchmark 2.92GPU, koro (CUDA) | 362.2 | 213.3 | B +69.8% |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 575.7 | 331 | B +73.9% |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 580.5 | 330.5 | B +75.7% |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 575.1 | 329.7 | B +74.4% |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 588.2 | 337.5 | B +74.3% |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 604.4 | 359 | B +68.4% |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 582.9 | 334.7 | B +74.1% |
| Blender Benchmark 2.81GPU, victor (CUDA) | 836.2 | 493.3 | B +69.5% |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 906.2 | 491.8 | B +84.3% |
| Blender Benchmark 2.82GPU, victor (CUDA) | 878.9 | 487.7 | B +80.2% |
| Blender Benchmark 2.83GPU, victor (CUDA) | 807.6 | 478.1 | B +68.9% |
| Blender Benchmark 2.90GPU, victor (CUDA) | 800.4 | 472.4 | B +69.4% |
| Blender Benchmark 2.92GPU, victor (CUDA) | 867.1 | 521.5 | B +66.2% |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 534.5 | 821.5 | B +53.7% |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 567.2 | 868 | B +53% |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 572.3 | 883.9 | B +54.4% |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 567.4 | 878.4 | B +54.8% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 567.6 | 879.8 | B +55% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 573.3 | 889.7 | B +55.2% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 574 | 889.8 | B +55% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 540.2 | 830.7 | B +53.8% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 548 | 842.2 | B +53.7% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 522.5 | 829 | B +58.7% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 527.1 | 820.8 | B +55.7% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (54)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 105.4 | 65.4 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (OPTIX) | 162.3 | — | no pair |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 107.8 | 61.8 | reference |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 109.1 | 61.3 | reference |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 329.9 | 193.9 | reference |
| Blender Benchmark 2.90.1GPU, classroom (OPTIX) | 630.3 | — | no pair |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 389.5 | 216.5 | reference |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 386.7 | 221.1 | reference |
| Blender Benchmark 2.93.1GPU, classroom (OPTIX) | 412.9 | 221.4 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 204 | 122.4 | reference |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | 205.8 | 115.4 | reference |
| Blender Benchmark 2.90.1GPU, fishy_cat (OPTIX) | 322.6 | — | no pair |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 200.3 | 115.5 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 204.8 | 119.4 | reference |
| Blender Benchmark 2.93.1GPU, fishy_cat (OPTIX) | 213.2 | 117.4 | reference |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 345.7 | 214.6 | reference |
| Blender Benchmark 2.90GPU, koro (OPTIX) | 239.7 | 132.1 | reference |
| Blender Benchmark 2.90.1GPU, koro (OPTIX) | 377.3 | — | no pair |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 228.9 | 133.7 | reference |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 316.7 | 172.2 | reference |
| Blender Benchmark 2.93.1GPU, koro (OPTIX) | 247.4 | 135.1 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 558.8 | 341.4 | reference |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | 579 | 330.9 | reference |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (OPTIX) | 873.9 | — | no pair |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 560.3 | 326.6 | reference |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 558.4 | 333.8 | reference |
| Blender Benchmark 2.93.1GPU, pavillon_barcelona (OPTIX) | 592.5 | 334.1 | reference |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 763.4 | 460.2 | reference |
| Blender Benchmark 2.90GPU, victor (OPTIX) | 778.6 | 447.9 | reference |
| Blender Benchmark 2.90.1GPU, victor (OPTIX) | 1,202.1 | — | no pair |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 752.1 | 436.1 | reference |
| Blender Benchmark 2.92GPU, victor (OPTIX) | 818.9 | 480.3 | reference |
| Blender Benchmark 2.93.1GPU, victor (OPTIX) | 848.4 | 462.5 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | 705.2 | 936.1 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 639.5 | 873.8 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 642.2 | 895.1 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | 653.8 | 976.1 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 619.2 | 931.9 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 647.6 | — | no pair |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 631.4 | 928.2 | reference |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 653 | 960.5 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 610.5 | — | no pair |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 662.3 | 886.4 | reference |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 606.7 | 905.1 | reference |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 628.7 | — | no pair |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 449.5 | 685.3 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 474.2 | 699.6 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 624.6 | 935.9 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 567.1 | 888.7 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 461.2 | 695.2 | reference |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 925.1 | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 969.1 | no pair |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 780.2 | no pair |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 726.9 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce GTX 1070 | B · GeForce GTX 1080 Ti | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | GP104-200-A1 | GP102-350-K1-A1 | differs |
| Architecture | Pascal | Pascal | equal |
| Shader unitsShader unit counts are comparable only within one architecture. | 1,920 (CUDA cores) | 3,584 (CUDA cores) | B: 1,664 more |
| Clocks | |||
| Base clock | 1,506 MHz | 1,481 MHz | A: 25 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,683 MHz | 1,582 MHz | A: 101 MHz more |
| Memory | |||
| Video memory | 8 GB | 11 GB | B: 3 GB more |
| Memory type | GDDR5 | GDDR5X | differs |
| Memory bus | 256 bit | 352 bit | B: 96 bit more |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | 256.3 GB/s | 484.4 GB/s | B: 228.1 GB/s 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. | 150 W (TDP) | 250 W (TDP) | B: 100 W higher |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 | equal |
Chip
GPU chip
AGP104-200-A1
BGP102-350-K1-A1
differsArchitecture
APascal
BPascal
equalShader units
A1,920 (CUDA cores)
B3,584 (CUDA cores)
B: 1,664 moreShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,506 MHz
B1,481 MHz
A: 25 MHz moreBoost clock
A1,683 MHz
B1,582 MHz
A: 101 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
A8 GB
B11 GB
B: 3 GB moreMemory type
AGDDR5
BGDDR5X
differsMemory bus
A256 bit
B352 bit
B: 96 bit moreMemory bandwidth
A256.3 GB/s
B484.4 GB/s
B: 228.1 GB/s moreExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A150 W (TDP)
B250 W (TDP)
B: 100 W higherTGP (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.
Interface
APCIe 3.0 x16
BPCIe 3.0 x16
equal
“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 GTX 1070 and NVIDIA GeForce GTX 1080 Ti have?
NVIDIA GeForce GTX 1070: 8 GB GDDR5, 256-bit bus. NVIDIA GeForce GTX 1080 Ti: 11 GB GDDR5X, 352-bit bus.
Which PCIe interface do the cards use?
NVIDIA GeForce GTX 1070: PCIe 3.0 x16. NVIDIA GeForce GTX 1080 Ti: PCIe 3.0 x16.
Which is faster: NVIDIA GeForce GTX 1070 or NVIDIA GeForce GTX 1080 Ti?
NVIDIA GeForce GTX 1080 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 (2)
- Wikipedia (English) — specifications of NVIDIA GeForce GTX 1070, specifications of NVIDIA GeForce GTX 1080 Ti, release date and launch pricechecked November 14, 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 2.90.1, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 3.1.0, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 3.2.1, 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 4.0.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 4.2.0, benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 5.1.0, benchmark Blender Benchmark 3.1.2, benchmark Blender Benchmark 5.0.0checked November 14, 2026
How we compare: methodology. Where the data comes from: sources.