GeForce RTX 4070 Ti vs GeForce RTX 4070 Ti SUPER: specs and benchmark comparison
ANVIDIA · Ada Lovelace
NVIDIA GeForce RTX 4070 Ti
- 12 GB GDDR6X
- 285 W
- PSU 700 W+
January 5, 2023 · $799 at launch
BNVIDIA · Ada Lovelace
NVIDIA GeForce RTX 4070 Ti SUPER
- 16 GB GDDR6X
- 285 W
- PSU 700 W+
January 24, 2024 · $799 at launch
Short verdict
NVIDIA GeForce RTX 4070 Ti SUPER 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 +13%NVIDIA GeForce RTX 4070 Ti SUPER leads in this scenario (up to 13% 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 4070 Ti is better0
No advantages found in our data.
Where GeForce RTX 4070 Ti SUPER is better4
Blender Benchmark 4.5.0 11.7% faster7,123 samples/min vs 6,379 samples/min
Shader units 768 more8,448 (CUDA cores) vs 7,680 (CUDA cores)
Video memory 4 GB more16 GB vs 12 GB
Memory bus 64 bit more256 bit vs 192 bit
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- B ahead by 11.7%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 4070 Ti6,378.9 samples/minGeForce RTX 4070 Ti SUPER7,122.7 samples/minPosition among tested models (67, OptiX)
A · 6,379B · 7,12305,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. NVIDIA GeForce RTX 4070 Ti SUPER is ahead by 11.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 4070 Ti
6,378.9 samples/min · community measurement, sample 142 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 142 submissions (14 outliers excluded), interquartile range 6264.98–6472.22; submissions 2025-07-17 to 2026-10-05; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce RTX 4070 Ti SUPER
7,122.7 samples/min · community measurement, sample 226 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 226 submissions (27 outliers excluded), interquartile range 6958.15–7262.73; submissions 2025-07-17 to 2026-07-06; 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) | 6,232.1 | 7,034.3 | B +12.9% |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,574.5 | 7,125.7 | B +8.4% |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,313.6 | 6,999.2 | B +10.9% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,302 | 8,143.7 | B +11.5% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,512.5 | 7,237.9 | B +11.1% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,532.1 | 7,327.6 | B +12.2% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,232.6 | 7,032.4 | B +12.8% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,315.3 | 7,134.6 | B +13% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (7)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,049.7 | — | no pair |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,086.2 | 8,012.6 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,093 | 6,722.4 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,374.1 | 8,158.6 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,462.8 | 6,554.7 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,519.5 | 7,194.7 | reference |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,260.4 | 7,538.3 | reference |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce RTX 4070 Ti | B · GeForce RTX 4070 Ti SUPER | Difference |
|---|---|---|---|
| Chip | |||
| Architecture | Ada Lovelace | Ada Lovelace | equal |
| Shader unitsShader unit counts are comparable only within one architecture. | 7,680 (CUDA cores) | 8,448 (CUDA cores) | B: 768 more |
| Clocks | |||
| Base clock | 2,310 MHz | 2,340 MHz | B: 30 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 2,610 MHz | 2,610 MHz | equal |
| Memory | |||
| Video memory | 12 GB | 16 GB | B: 4 GB more |
| Memory type | GDDR6X | GDDR6X | equal |
| Memory bus | 192 bit | 256 bit | B: 64 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. | 285 W (TGP) | 285 W (TGP) | equal |
| Recommended PSU | 700 W | 700 W | equal |
Chip
Architecture
AAda Lovelace
BAda Lovelace
equalShader units
A7,680 (CUDA cores)
B8,448 (CUDA cores)
B: 768 moreShader unit counts are comparable only within one architecture.
Clocks
Base clock
A2,310 MHz
B2,340 MHz
B: 30 MHz moreBoost clock
A2,610 MHz
B2,610 MHz
equalClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit.
Memory
Video memory
A12 GB
B16 GB
B: 4 GB moreMemory type
AGDDR6X
BGDDR6X
equalMemory bus
A192 bit
B256 bit
B: 64 bit more
Power and dimensions
Board power
A285 W (TGP)
B285 W (TGP)
equalTGP (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
A700 W
B700 W
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 4070 Ti and NVIDIA GeForce RTX 4070 Ti SUPER have?
NVIDIA GeForce RTX 4070 Ti: 12 GB GDDR6X, 192-bit bus. NVIDIA GeForce RTX 4070 Ti SUPER: 16 GB GDDR6X, 256-bit bus.
What power supply does the manufacturer recommend?
For NVIDIA GeForce RTX 4070 Ti, 700 W or more; for NVIDIA GeForce RTX 4070 Ti SUPER, 700 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 4070 Ti or NVIDIA GeForce RTX 4070 Ti SUPER?
NVIDIA GeForce RTX 4070 Ti SUPER 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 4070 Ti, specifications of NVIDIA GeForce RTX 4070 Ti SUPERchecked November 7, 2026
- Blender Open Data (Blender Foundation) — 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 3.3.0, 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 4.3.0, benchmark Blender Benchmark 4.4.0, benchmark Blender Benchmark 5.0.0, benchmark Blender Benchmark 5.1.0, benchmark Blender Benchmark 5.3.0, benchmark Blender Benchmark 3.2.1checked November 14, 2026
- Wikipedia (English) — release date and launch pricechecked November 14, 2026
How we compare: methodology. Where the data comes from: sources.