GeForce RTX 4070 SUPER vs GeForce RTX 4070 Ti SUPER: specs and benchmark comparison
ANVIDIA · Ada Lovelace
NVIDIA GeForce RTX 4070 SUPER
- 12 GB GDDR6X
- 220 W
- PSU 650 W+
January 17, 2024 · $599 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 +17.6%NVIDIA GeForce RTX 4070 Ti SUPER leads in this scenario (up to 17.6% 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 SUPER is better2
Board power 65 W lower220 W (TGP) vs 285 W (TGP)
Launch price $200 lower$599 vs $799
Where GeForce RTX 4070 Ti SUPER is better4
Blender Benchmark 4.5.0 13.6% faster7,123 samples/min vs 6,268 samples/min
Shader units 1,280 more8,448 (CUDA cores) vs 7,168 (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 13.6%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce RTX 4070 SUPER6,267.9 samples/minGeForce RTX 4070 Ti SUPER7,122.7 samples/minPosition among tested models (67, OptiX)
A · 6,268B · 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 13.6% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce RTX 4070 SUPER
6,267.9 samples/min · community measurement, sample 448 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 448 submissions (21 outliers excluded), interquartile range 6009.46–6439.99; submissions 2025-07-17 to 2026-11-11; 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) | 6,067.5 | 7,034.3 | B +15.9% |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,209.5 | 7,125.7 | B +14.8% |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,970.4 | 6,999.2 | B +17.2% |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,923.4 | 8,143.7 | B +17.6% |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,370.1 | 7,237.9 | B +13.6% |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,352.9 | 7,327.6 | B +15.3% |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,078.3 | 7,032.4 | B +15.7% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,169.7 | 7,134.6 | B +15.6% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (12)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 4,070.7 | — | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 3,969.7 | — | no pair |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 3,989.7 | — | no pair |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 4,090.2 | — | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 4,088 | — | no pair |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,140.3 | — | no pair |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,920.2 | 8,012.6 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,990.3 | 6,722.4 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,903.7 | 8,158.6 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 5,931.9 | 6,554.7 | reference |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 6,113.7 | 7,194.7 | reference |
| Blender Benchmark 5.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 7,092.6 | 7,538.3 | reference |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce RTX 4070 SUPER | B · GeForce RTX 4070 Ti SUPER | Difference |
|---|---|---|---|
| Chip | |||
| Architecture | Ada Lovelace | Ada Lovelace | equal |
| Shader unitsShader unit counts are comparable only within one architecture. | 7,168 (CUDA cores) | 8,448 (CUDA cores) | B: 1,280 more |
| Clocks | |||
| Base clock | 1,980 MHz | 2,340 MHz | B: 360 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 2,480 MHz | 2,610 MHz | B: 130 MHz more |
| 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. | 220 W (TGP) | 285 W (TGP) | B: 65 W higher |
| Recommended PSU | 650 W | 700 W | B: 50 W higher |
| Interface | PCIe 4.0 | no data | no data for B |
| Length (reference / Founders Edition)Partner cards have different dimensions; check the specific SKU. | 244 mm | no data | no data for B |
| Thickness (slots) | 2 | no data | no data for B |
| Power connectors (reference) | 1x 16-pin (adapter to 2x 8-pin included) — Founders Edition | no data | no data for B |
Chip
Architecture
AAda Lovelace
BAda Lovelace
equalShader units
A7,168 (CUDA cores)
B8,448 (CUDA cores)
B: 1,280 moreShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,980 MHz
B2,340 MHz
B: 360 MHz moreBoost clock
A2,480 MHz
B2,610 MHz
B: 130 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
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
A220 W (TGP)
B285 W (TGP)
B: 65 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
A650 W
B700 W
B: 50 W higherInterface
APCIe 4.0
Bno data
no data for BLength (reference / Founders Edition)
A244 mm
Bno data
no data for BPartner cards have different dimensions; check the specific SKU.
Thickness (slots)
A2
Bno data
no data for BPower connectors (reference)
A1x 16-pin (adapter to 2x 8-pin included) — Founders Edition
Bno data
no data for B
“More” does not always mean “better”: higher power draw or size is a system requirement, not an advantage (such bars are dimmed).
Compare with AI
An AI model reviews the specs and benchmarks of this pair and gives a plain-language verdict on who each model suits.
Questions and answers
How much video memory do NVIDIA GeForce RTX 4070 SUPER and NVIDIA GeForce RTX 4070 Ti SUPER have?
NVIDIA GeForce RTX 4070 SUPER: 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 SUPER, 650 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 SUPER 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 SUPER, specifications of NVIDIA GeForce RTX 4070 Ti SUPERchecked November 7, 2026
- Blender Open Data (Blender Foundation) — 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 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 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.