GeForce GTX 1660 Ti vs GeForce GTX 970: specs and benchmark comparison
Short verdict
NVIDIA GeForce GTX 1660 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
A +200.5%NVIDIA GeForce GTX 1660 Ti leads in this scenario (up to 200.5% 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 1660 Ti is better7
Blender Benchmark 2.93.1 35.9% lower84 s vs 114 s
Blender Benchmark 2.90 44.7% lower333 s vs 482 s
Blender Benchmark 4.5.0 195.5% faster753 samples/min vs 255 samples/min
Video memory 2 GB more6 GB vs 4 GB
Memory bandwidth 63.6 GB/s more288 GB/s vs 224.4 GB/s
Board power 28 W lower120 W (TDP) vs 148 W (TDP)
Launch price $50 lower$279 vs $329
Where GeForce GTX 970 is better1
Memory bus 64 bit more256 bit vs 192 bit
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- A ahead by 35.9%
Blender Benchmark 2.93.1
GPU, bmw27 (CUDA) · s, lower is better
GeForce GTX 1660 Ti84.2 sGeForce GTX 970114.4 sPosition among tested models (31, CUDA)
A · 84B · 1140100200300Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1660 Ti is ahead by 35.9% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1660 Ti
84.2 s · community measurement, sample 43 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 43 submissions (0 outliers excluded), interquartile range 80.69–88.8; submissions 2021-07-14 to 2022-02-26; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 970
114.4 s · community measurement, sample 24 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 24 submissions (0 outliers excluded), interquartile range 110.31–115.83; submissions 2021-07-15 to 2022-02-28; 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 44.7%
Blender Benchmark 2.90
GPU, classroom (CUDA) · s, lower is better
GeForce GTX 1660 Ti333.4 sGeForce GTX 970482.4 sPosition among tested models (25, CUDA)
A · 333B · 4820200400600800Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1660 Ti is ahead by 44.7% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1660 Ti
333.4 s · community measurement, sample 105 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 105 submissions (8 outliers excluded), interquartile range 325.46–343.87; submissions 2020-09-02 to 2021-02-04; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 970
482.4 s · community measurement, sample 23 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 23 submissions (1 outliers excluded), interquartile range 477.87–497.56; submissions 2020-09-02 to 2021-01-28; 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 195.5%
Blender Benchmark 4.5.0
GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) · samples/min, higher is better
GeForce GTX 1660 Ti752.7 samples/minGeForce GTX 970254.8 samples/minPosition among tested models (67, OptiX)
B · 255A · 75305,00010,00015,000Each dot is one model’s median in this benchmark. The scale starts at zero, samples/min. NVIDIA GeForce GTX 1660 Ti is ahead by 195.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1660 Ti
752.7 samples/min · community measurement, sample 58 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 58 submissions (4 outliers excluded), interquartile range 713.01–780.43; submissions 2025-07-17 to 2026-07-24; OPTIX backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 970
254.8 samples/min · community measurement, sample 22 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 22 submissions (0 outliers excluded), interquartile range 247.96–284.19; submissions 2025-07-22 to 2026-07-11; 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 (5)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 91.7 | 141.2 | A +54% |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 92.4 | 152.5 | A +65.1% |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 98.6 | 149 | A +51.2% |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 322.2 | 473.5 | A +47% |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 753.9 | 250.9 | A +200.5% |
Each benchmark version has its own scale: numbers are compared only within a row.
Reference results (96)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81GPU, barbershop_interior (CUDA) | 1,104.2 | 1,843.1 | reference |
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 1,122.6 | 1,839.1 | reference |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 90.5 | 146.8 | reference |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 90.2 | 144.6 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 94.2 | 165.1 | reference |
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 97.3 | 179.3 | reference |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 74.2 | 166.6 | reference |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 74.5 | 167.4 | reference |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 72.3 | 162.3 | reference |
| Blender Benchmark 2.93.1GPU, bmw27 (OPTIX) | 78 | 157.1 | reference |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 331 | 475.9 | reference |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 333 | 480 | reference |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 328 | 482.6 | reference |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 338.7 | 458.5 | reference |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 341.5 | 475.4 | reference |
| Blender Benchmark 2.93.1GPU, classroom (CUDA) | 300.4 | 402.7 | reference |
| Blender Benchmark 2.90GPU, classroom (OPTIX) | 298 | 673.3 | reference |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 302.3 | 617.5 | reference |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 289.8 | 667.8 | reference |
| Blender Benchmark 2.93.1GPU, classroom (OPTIX) | 307.1 | 605.8 | reference |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 166.2 | 314.6 | reference |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 168.3 | 312.1 | reference |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 173.3 | 309.2 | reference |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 177.1 | 310.9 | reference |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 185.6 | 303.2 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 169.5 | 343.7 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 183.9 | 365.2 | reference |
| Blender Benchmark 2.93.1GPU, fishy_cat (CUDA) | 169.5 | 365 | reference |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | 146.3 | 452.8 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 148.8 | 348 | reference |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 158.6 | — | no pair |
| Blender Benchmark 2.93.1GPU, fishy_cat (OPTIX) | 165.4 | 392.5 | reference |
| Blender Benchmark 2.81GPU, koro (CUDA) | 286.5 | 666.3 | reference |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 288.5 | 673.6 | reference |
| Blender Benchmark 2.82GPU, koro (CUDA) | 284.9 | 645.5 | reference |
| Blender Benchmark 2.83GPU, koro (CUDA) | 302.4 | 862.4 | reference |
| Blender Benchmark 2.90GPU, koro (CUDA) | 298 | 558.8 | reference |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 275 | 516.5 | reference |
| Blender Benchmark 2.92GPU, koro (CUDA) | 286.2 | 714.1 | reference |
| Blender Benchmark 2.93.1GPU, koro (CUDA) | 269.1 | 619.8 | reference |
| Blender Benchmark 2.90GPU, koro (OPTIX) | 182.5 | 535.2 | reference |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 182 | 443.9 | reference |
| Blender Benchmark 2.93.1GPU, koro (OPTIX) | 230 | 419.4 | reference |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 548.6 | 773.7 | reference |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 546.1 | 782.3 | reference |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 543.8 | 761.3 | reference |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 546.7 | 803.2 | reference |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 577.5 | 784 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 528.2 | 830 | reference |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 538.2 | 927.5 | reference |
| Blender Benchmark 2.93.1GPU, pavillon_barcelona (CUDA) | 481.4 | 689.5 | reference |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | 429.1 | 1,050.6 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 427 | 939.8 | reference |
| Blender Benchmark 2.93.1GPU, pavillon_barcelona (OPTIX) | 454.8 | 903.5 | reference |
| Blender Benchmark 2.81GPU, victor (CUDA) | 712.3 | 3,321.1 | reference |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 718.6 | 5,776.8 | reference |
| Blender Benchmark 2.82GPU, victor (CUDA) | 704.2 | 3,504.1 | reference |
| Blender Benchmark 2.83GPU, victor (CUDA) | 708.4 | — | no pair |
| Blender Benchmark 2.90GPU, victor (CUDA) | 709.3 | 9,949 | reference |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 684.3 | 9,881.1 | reference |
| Blender Benchmark 2.92GPU, victor (CUDA) | 805.1 | 3,277.2 | reference |
| Blender Benchmark 2.93.1GPU, victor (CUDA) | 706.2 | — | no pair |
| Blender Benchmark 2.90GPU, victor (OPTIX) | 585.4 | 3,604.7 | reference |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 598.2 | 2,482 | reference |
| Blender Benchmark 2.93.1GPU, victor (OPTIX) | 690.1 | 2,414.8 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 851.2 | 342 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | 883.7 | 335.6 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 898.2 | 333.3 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 849.6 | 320 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 907.5 | — | no pair |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 971.3 | 447.6 | reference |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 773.7 | — | no pair |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 777.5 | — | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 763.4 | 268.8 | reference |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 702.6 | 218.9 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 685.6 | 244 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 888.1 | 333.4 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 820.5 | 302.6 | reference |
| Blender Benchmark 3.1.2GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 875.8 | — | no pair |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 813 | 286.9 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 810.8 | 306.3 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 825.9 | 276 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 825.2 | 277.8 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 862.4 | 327.6 | reference |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 854.4 | 301.1 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 781.6 | 288.9 | reference |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 788.7 | 258.9 | reference |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 765.6 | 247.1 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 686.9 | — | no pair |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 698.7 | 249 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (CUDA) | — | 149.8 | no pair |
| Blender Benchmark 2.90.1GPU, classroom (CUDA) | — | 487.8 | no pair |
| Blender Benchmark 2.90.1GPU, fishy_cat (CUDA) | — | 303.8 | no pair |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 363.4 | no pair |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 310.5 | no pair |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 251.5 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce GTX 1660 Ti | B · GeForce GTX 970 | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | TU116-400-A1 | GM204-200-A1 | differs |
| Architecture | Turing | Maxwell | differs |
| Shader unitsShader unit counts are comparable only within one architecture. | 1,536 (CUDA cores) | 1,664 (CUDA cores) | not directly comparable |
| Clocks | |||
| Base clock | 1,500 MHz | 1,050 MHz | A: 450 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 | 1,178 MHz | A: 592 MHz more |
| Memory | |||
| Video memory | 6 GB | 4 GB | A: 2 GB more |
| Memory type | GDDR6 | GDDR5 | differs |
| Memory bus | 192 bit | 256 bit | B: 64 bit more |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | 288 GB/s | 224.4 GB/s | A: 63.6 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. | 120 W (TDP) | 148 W (TDP) | B: 28 W higher |
Chip
GPU chip
ATU116-400-A1
BGM204-200-A1
differsArchitecture
ATuring
BMaxwell
differsShader units
A1,536 (CUDA cores)
B1,664 (CUDA cores)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,500 MHz
B1,050 MHz
A: 450 MHz moreBoost clock
A1,770 MHz
B1,178 MHz
A: 592 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
A6 GB
B4 GB
A: 2 GB moreMemory type
AGDDR6
BGDDR5
differsMemory bus
A192 bit
B256 bit
B: 64 bit moreMemory bandwidth
A288 GB/s
B224.4 GB/s
A: 63.6 GB/s moreExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A120 W (TDP)
B148 W (TDP)
B: 28 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.
“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 1660 Ti and NVIDIA GeForce GTX 970 have?
NVIDIA GeForce GTX 1660 Ti: 6 GB GDDR6, 192-bit bus. NVIDIA GeForce GTX 970: 4 GB GDDR5, 256-bit bus.
Which is faster: NVIDIA GeForce GTX 1660 Ti or NVIDIA GeForce GTX 970?
NVIDIA GeForce GTX 1660 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 1660 Ti, specifications of NVIDIA GeForce GTX 970, 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 3.1.0, 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 4.2.0, benchmark Blender Benchmark 5.2.0, benchmark Blender Benchmark 3.0.1, benchmark Blender Benchmark 4.3.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 4.5.0, benchmark Blender Benchmark 3.1.2, benchmark Blender Benchmark 3.2.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.1.0, 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.