GeForce RTX 3070 Ti vs GeForce RTX 3090: specs and benchmark comparison
BNVIDIA · Ampere
NVIDIA GeForce RTX 3090
- 24 GB GDDR6X
- 350 W
- PSU 750 W+
September 24, 2020 · $1,499 at launch
Short verdict
NVIDIA GeForce RTX 3090 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 +73%NVIDIA GeForce RTX 3090 leads in this scenario (up to 73% 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 3070 Ti is better2
Board power 60 W lower290 W (board power) vs 350 W (board power)
Launch price $900 lower$599 vs $1,499
Where GeForce RTX 3090 is better16
Blender Benchmark 2.93.1 49.3% lower17 s vs 25 s
Blender Benchmark 2.93.1 59.3% lower9 s vs 15 s
Blender Benchmark 2.93.1 39.1% lower80 s vs 111 s
Blender Benchmark 2.93.1 48.6% lower33 s vs 50 s
Blender Benchmark 2.93.1 55% lower34 s vs 53 s
Blender Benchmark 2.93.1 66.6% lower18 s vs 30 s
Blender Benchmark 2.93.1 62% lower55 s vs 88 s
Blender Benchmark 2.93.1 66.6% lower38 s vs 63 s
Blender Benchmark 2.93.1 49.7% lower99 s vs 149 s
Blender Benchmark 2.93.1 51.7% lower45 s vs 68 s
Blender Benchmark 2.93.1 54.8% lower139 s vs 215 s
Blender Benchmark 2.93.1 54.5% lower60 s vs 93 s
Blender Benchmark 4.5.0 54.3% faster5,424 samples/min vs 3,514 samples/min
Shader units 4,352 more10,496 (CUDA cores) vs 6,144 (CUDA cores)
Video memory 16 GB more24 GB vs 8 GB
Memory bus 128 bit more384 bit vs 256 bit
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- B ahead by 49.3%
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce RTX 3070 Ti25.3 sGeForce RTX 309016.9 sPosition among tested models (31, CUDA)
B · 17A · 250100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 49.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
25.3 s · community measurement, sample 90 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 90 submissions (19 outliers excluded), interquartile range 25.14–25.68; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
16.9 s · community measurement, sample 279 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 279 submissions (58 outliers excluded), interquartile range 16.76–17.19; submissions 2021-07-09 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 59.3%
Blender Benchmark 2.93.1
GPU, bmw27 (OPTIX) · s, lower is better
GeForce RTX 3070 Ti14.8 sGeForce RTX 30909.3 sPosition among tested models (20, OptiX)
B · 9A · 15050100150Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 59.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
14.8 s · community measurement, sample 42 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 42 submissions (7 outliers excluded), interquartile range 14.72–15.04; submissions 2021-07-10 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
9.3 s · community measurement, sample 244 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 244 submissions (56 outliers excluded), interquartile range 9.17–9.43; submissions 2021-07-10 to 2022-02-28; 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 39.1%
Blender Benchmark 2.93.1
GPU, classroom (CUDA) · s, lower is better
GeForce RTX 3070 Ti110.6 sGeForce RTX 309079.5 sPosition among tested models (26, CUDA)
B · 80A · 1110200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 39.1% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
110.6 s · community measurement, sample 73 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 73 submissions (15 outliers excluded), interquartile range 108.88–111.47; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
79.5 s · community measurement, sample 260 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 260 submissions (43 outliers excluded), interquartile range 78.58–81; submissions 2021-07-09 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 48.6%
Blender Benchmark 2.93.1
GPU, classroom (OPTIX) · s, lower is better
GeForce RTX 3070 Ti49.8 sGeForce RTX 309033.5 sPosition among tested models (14, OptiX)
B · 33A · 50050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 48.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
49.8 s · community measurement, sample 42 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 42 submissions (4 outliers excluded), interquartile range 49.1–50.9; submissions 2021-07-10 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
33.5 s · community measurement, sample 182 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 182 submissions (15 outliers excluded), interquartile range 32.84–34.67; submissions 2021-07-10 to 2022-02-28; 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 55%
Blender Benchmark 2.93.1
GPU, fishy_cat (CUDA) · s, lower is better
GeForce RTX 3070 Ti53.4 sGeForce RTX 309034.4 sPosition among tested models (21, CUDA)
B · 34A · 530100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 55% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
53.4 s · community measurement, sample 65 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 65 submissions (10 outliers excluded), interquartile range 52.81–54.09; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
34.4 s · community measurement, sample 213 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 213 submissions (51 outliers excluded), interquartile range 34.13–34.9; submissions 2021-07-09 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 66.6%
Blender Benchmark 2.93.1
GPU, fishy_cat (OPTIX) · s, lower is better
GeForce RTX 3070 Ti29.9 sGeForce RTX 309017.9 sPosition among tested models (13, OptiX)
B · 18A · 30020406080Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 66.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
29.9 s · community measurement, sample 32 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 32 submissions (3 outliers excluded), interquartile range 29.51–30.21; submissions 2021-07-10 to 2022-02-14; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
17.9 s · community measurement, sample 141 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 141 submissions (40 outliers excluded), interquartile range 17.77–18.14; submissions 2021-07-10 to 2022-02-28; 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 62%
Blender Benchmark 2.93.1
GPU, koro (CUDA) · s, lower is better
GeForce RTX 3070 Ti88.4 sGeForce RTX 309054.6 sPosition among tested models (20, CUDA)
B · 55A · 880200400600Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 62% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
88.4 s · community measurement, sample 60 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 60 submissions (11 outliers excluded), interquartile range 87.85–89.37; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
54.6 s · community measurement, sample 216 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 216 submissions (47 outliers excluded), interquartile range 54.03–55.35; submissions 2021-07-09 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 66.6%
Blender Benchmark 2.93.1
GPU, koro (OPTIX) · s, lower is better
GeForce RTX 3070 Ti63.2 sGeForce RTX 309037.9 sPosition among tested models (13, OptiX)
B · 38A · 63050100150200Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 66.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
63.2 s · community measurement, sample 34 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 34 submissions (0 outliers excluded), interquartile range 62.36–64.49; submissions 2021-07-10 to 2022-02-14; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
37.9 s · community measurement, sample 143 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 143 submissions (36 outliers excluded), interquartile range 37.49–38.45; submissions 2021-07-10 to 2022-02-28; 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 49.7%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (CUDA) · s, lower is better
GeForce RTX 3070 Ti148.7 sGeForce RTX 309099.3 sPosition among tested models (21, CUDA)
B · 99A · 1490200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 49.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
148.7 s · community measurement, sample 60 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 60 submissions (12 outliers excluded), interquartile range 147.41–150.7; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
99.3 s · community measurement, sample 215 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 215 submissions (50 outliers excluded), interquartile range 98.46–100.87; submissions 2021-07-09 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 51.7%
Blender Benchmark 2.93.1
GPU, pavillon_barcelona (OPTIX) · s, lower is better
GeForce RTX 3070 Ti68.4 sGeForce RTX 309045.1 sPosition among tested models (13, OptiX)
B · 45A · 680100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 51.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
68.4 s · community measurement, sample 37 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 37 submissions (3 outliers excluded), interquartile range 67.81–69.84; submissions 2021-07-10 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
45.1 s · community measurement, sample 145 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 145 submissions (26 outliers excluded), interquartile range 44.57–45.81; submissions 2021-07-10 to 2022-02-28; 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 54.8%
Blender Benchmark 2.93.1
GPU, victor (CUDA) · s, lower is better
GeForce RTX 3070 Ti214.7 sGeForce RTX 3090138.7 sPosition among tested models (19, CUDA)
B · 139A · 21502505007501,000Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 54.8% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
214.7 s · community measurement, sample 52 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 52 submissions (15 outliers excluded), interquartile range 213.55–217.22; submissions 2021-07-12 to 2022-02-27; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
138.7 s · community measurement, sample 217 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 217 submissions (43 outliers excluded), interquartile range 137.5–140.78; submissions 2021-07-09 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 54.5%
Blender Benchmark 2.93.1
GPU, victor (OPTIX) · s, lower is better
GeForce RTX 3070 Ti93.4 sGeForce RTX 309060.4 sPosition among tested models (13, OptiX)
B · 60A · 930100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce RTX 3090 is ahead by 54.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
93.4 s · community measurement, sample 35 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 35 submissions (0 outliers excluded), interquartile range 92.93–96.09; submissions 2021-07-10 to 2022-02-21; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
60.4 s · community measurement, sample 144 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 144 submissions (24 outliers excluded), interquartile range 59.46–61.01; submissions 2021-07-10 to 2022-02-28; 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 54.3%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 3070 Ti3,514.2 samples/minGeForce RTX 30905,423.6 samples/minPosition among tested models (67, OptiX)
A · 3,514B · 5,42405,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. NVIDIA GeForce RTX 3090 is ahead by 54.3% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 3070 Ti
3,514.2 samples/min · community measurement, sample 109 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 109 submissions (9 outliers excluded), interquartile range 3371.91–3561.39; submissions 2025-07-17 to 2026-11-11; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 3090
5,423.6 samples/min · community measurement, sample 596 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 596 submissions (34 outliers excluded), interquartile range 5240.15–5558.47; 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 (15)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,488.7 | 5,354.8 | B +53.5% |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,286.8 | 5,253.3 | B +59.8% |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,395.4 | 5,093.8 | B +50% |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,849.2 | 5,841.8 | B +51.8% |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,793 | 6,560.4 | B +73% |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,805.6 | 6,566.2 | B +72.5% |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,795.9 | 5,625.7 | B +48.2% |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,888.7 | 6,018.2 | B +54.8% |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,891.1 | 6,014.6 | B +54.6% |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 4,130.4 | 6,296.9 | B +52.5% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 4,100.2 | 6,305.5 | B +53.8% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,599.4 | 5,536.1 | B +53.8% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,624.6 | 5,536.4 | B +52.7% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,495.5 | 5,347.6 | B +53% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,501.2 | 5,333 | B +52.3% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (65)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 28.5 | 18.5 | reference |
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 27.8 | 18.5 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 13.7 | 9.2 | reference |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 14 | 9.1 | reference |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 81.9 | 58.8 | reference |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 79.3 | 55.5 | reference |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 48.1 | 37.1 | reference |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 48.9 | 34.4 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 52.8 | 33.9 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 53.8 | 34.8 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 27 | 16.7 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 29.4 | 18.4 | reference |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 92 | 57.5 | reference |
| Blender Benchmark 2.92GPU, koro (CUDA) | 92.1 | 58 | reference |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 60.5 | 36.3 | reference |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 64.4 | 57.1 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 164.2 | 108.5 | reference |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 164.4 | 109.3 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 66.6 | 46.9 | reference |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 65.9 | 45.1 | reference |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 195.7 | 124.3 | reference |
| Blender Benchmark 2.92GPU, victor (CUDA) | 259.7 | 178.3 | reference |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 77.7 | 53.9 | reference |
| Blender Benchmark 2.92GPU, victor (OPTIX) | 93.5 | 62.5 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,299.5 | 3,418.3 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,102.2 | 3,138.2 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,039.7 | 3,729.7 | reference |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,605 | 4,060.8 | reference |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 2,339.1 | 3,699.3 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,076.6 | 4,875.8 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,325.5 | 5,266.1 | reference |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 3,665.8 | 5,143.8 | reference |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | — | 21.5 | no pair |
| Blender Benchmark 2.90.1GPU, bmw27 (CUDA) | — | 20.5 | no pair |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | — | 8.9 | no pair |
| Blender Benchmark 2.90.1GPU, bmw27 (OPTIX) | — | 8.9 | no pair |
| Blender Benchmark 2.90GPU, classroom (CUDA) | — | 70.6 | no pair |
| Blender Benchmark 2.90.1GPU, classroom (CUDA) | — | 67.4 | no pair |
| Blender Benchmark 2.90GPU, classroom (OPTIX) | — | 35.2 | no pair |
| Blender Benchmark 2.90.1GPU, classroom (OPTIX) | — | 38.9 | no pair |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | — | 39 | no pair |
| Blender Benchmark 2.90.1GPU, fishy_cat (CUDA) | — | 37.3 | no pair |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | — | 16.5 | no pair |
| Blender Benchmark 2.90.1GPU, fishy_cat (OPTIX) | — | 16.8 | no pair |
| Blender Benchmark 2.90GPU, koro (CUDA) | — | 58 | no pair |
| Blender Benchmark 2.90.1GPU, koro (CUDA) | — | 57.5 | no pair |
| Blender Benchmark 2.90GPU, koro (OPTIX) | — | 36.5 | no pair |
| Blender Benchmark 2.90.1GPU, koro (OPTIX) | — | 37.1 | no pair |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | — | 119.6 | no pair |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (CUDA) | — | 108.8 | no pair |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | — | 45.4 | no pair |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (OPTIX) | — | 46.6 | no pair |
| Blender Benchmark 2.90GPU, victor (CUDA) | — | 159.1 | no pair |
| Blender Benchmark 2.90.1GPU, victor (CUDA) | — | 148.7 | no pair |
| Blender Benchmark 2.90GPU, victor (OPTIX) | — | 52.8 | no pair |
| Blender Benchmark 2.90.1GPU, victor (OPTIX) | — | 57.7 | no pair |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,696.5 | no pair |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,448.2 | no pair |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,797.9 | no pair |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,864 | no pair |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,724.8 | no pair |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,735.6 | no pair |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,730.8 | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 3,798 | no pair |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | — | 5,826.5 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce RTX 3070 Ti | B · GeForce RTX 3090 | Difference |
|---|---|---|---|
| Chip | |||
| Architecture | Ampere | Ampere | equal |
| Shader unitsShader unit counts are comparable only within one architecture. | 6,144 (CUDA cores) | 10,496 (CUDA cores) | B: 4,352 more |
| Clocks | |||
| Base clock | 1,580 MHz | 1,400 MHz | A: 180 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,770 MHz | 1,700 MHz | A: 70 MHz more |
| Memory | |||
| Video memory | 8 GB | 24 GB | B: 16 GB more |
| Memory type | GDDR6X | GDDR6X | equal |
| Memory bus | 256 bit | 384 bit | B: 128 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. | 290 W (board power) | 350 W (board power) | B: 60 W higher |
| Recommended PSU | 750 W | 750 W | equal |
| Length (reference / Founders Edition)Partner cards have different dimensions; check the specific SKU. | 267 mm | 313 mm | B: 46 mm higher |
| Thickness (slots) | 2 | 3 | B: 1 higher |
| Power connectors (reference) | 2x 8-pin (adapter to 1x 12-pin included) — FE | 2x 8-pin (adapter to 1x 12-pin included) — FE | equal |
Chip
Architecture
AAmpere
BAmpere
equalShader units
A6,144 (CUDA cores)
B10,496 (CUDA cores)
B: 4,352 moreShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,580 MHz
B1,400 MHz
A: 180 MHz moreBoost clock
A1,770 MHz
B1,700 MHz
A: 70 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
B24 GB
B: 16 GB moreMemory type
AGDDR6X
BGDDR6X
equalMemory bus
A256 bit
B384 bit
B: 128 bit more
Power and dimensions
Board power
A290 W (board power)
B350 W (board power)
B: 60 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.
Recommended PSU
A750 W
B750 W
equalLength (reference / Founders Edition)
A267 mm
B313 mm
B: 46 mm higherPartner cards have different dimensions; check the specific SKU.
Thickness (slots)
A2
B3
B: 1 higherPower connectors (reference)
A2x 8-pin (adapter to 1x 12-pin included) — FE
B2x 8-pin (adapter to 1x 12-pin included) — FE
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 RTX 3070 Ti and NVIDIA GeForce RTX 3090 have?
NVIDIA GeForce RTX 3070 Ti: 8 GB GDDR6X, 256-bit bus. NVIDIA GeForce RTX 3090: 24 GB GDDR6X, 384-bit bus.
What power supply does the manufacturer recommend?
For NVIDIA GeForce RTX 3070 Ti, 750 W or more; for NVIDIA GeForce RTX 3090, 750 W or more. This is a recommendation for a typical system; also check the power connectors of the specific card model.
Which is faster: NVIDIA GeForce RTX 3070 Ti or NVIDIA GeForce RTX 3090?
NVIDIA GeForce RTX 3090 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 3070 Ti, specifications of NVIDIA GeForce RTX 3090checked November 7, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 2.90, benchmark Blender Benchmark 2.90.1, benchmark Blender Benchmark 2.91.2, benchmark Blender Benchmark 2.92, benchmark Blender Benchmark 2.93.1, 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 4.5.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.1.2, 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.