GeForce GTX 1650 vs GeForce GTX 960: specs and benchmark comparison
Short verdict
NVIDIA GeForce GTX 1650 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 +56.5%NVIDIA GeForce GTX 1650 leads in this scenario (up to 56.5% 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 1650 is better3
Blender Benchmark 2.90 56.5% lower158 s vs 248 s
Video memory 2 GB more4 GB vs 2 GB
Launch price $50 lower$149 vs $199
Where GeForce GTX 960 is better0
No advantages found in our data.
Benchmarks
Results are compared within one benchmark, one version and the same conditions.
- A ahead by 56.5%
Blender Benchmark 2.90
GPU, bmw27 (CUDA) · s, lower is better
GeForce GTX 1650158.3 sGeForce GTX 960247.7 sPosition among tested models (27, CUDA)
A · 158B · 2480100200300400Each dot is one model’s median in this benchmark. The scale starts at zero, s. NVIDIA GeForce GTX 1650 is ahead by 56.5% in this benchmark.
About the measurement and source
- A · NVIDIA GeForce GTX 1650
158.3 s · community measurement, sample 89 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 89 submissions (7 outliers excluded), interquartile range 154.87–163.22; submissions 2020-09-03 to 2021-12-13; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 960
247.7 s · community measurement, sample 21 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 21 submissions (2 outliers excluded), interquartile range 242.66–252.6; submissions 2020-09-04 to 2021-01-31; 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.
Reference results (108)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.81aGPU, barbershop_interior (CUDA) | 1,732.3 | — | no pair |
| Blender Benchmark 2.81GPU, bmw27 (CUDA) | 147.7 | 250.3 | reference |
| Blender Benchmark 2.81aGPU, bmw27 (CUDA) | 147.5 | 251.5 | reference |
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 149.1 | 246.4 | reference |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 153.3 | 259.4 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (CUDA) | 156.1 | — | no pair |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 157.6 | — | no pair |
| Blender Benchmark 2.92GPU, bmw27 (CUDA) | 156.3 | 319.1 | reference |
| Blender Benchmark 2.93.1GPU, bmw27 (CUDA) | 134.4 | 195.1 | reference |
| Blender Benchmark 2.90GPU, bmw27 (OPTIX) | 130.3 | 325.3 | reference |
| Blender Benchmark 2.90.1GPU, bmw27 (OPTIX) | 137.3 | — | no pair |
| Blender Benchmark 2.91.2GPU, bmw27 (OPTIX) | 126.2 | 290.1 | reference |
| Blender Benchmark 2.92GPU, bmw27 (OPTIX) | 127.4 | 345.3 | reference |
| Blender Benchmark 2.93.1GPU, bmw27 (OPTIX) | 133.9 | 355 | reference |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | 538.9 | 825.7 | reference |
| Blender Benchmark 2.82GPU, classroom (CUDA) | 516.2 | 829.6 | reference |
| Blender Benchmark 2.83GPU, classroom (CUDA) | 536.1 | 819.8 | reference |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 540.8 | 829.3 | reference |
| Blender Benchmark 2.90.1GPU, classroom (CUDA) | 571.1 | — | no pair |
| Blender Benchmark 2.91.2GPU, classroom (CUDA) | 549.2 | — | no pair |
| Blender Benchmark 2.92GPU, classroom (CUDA) | 572 | 824.5 | reference |
| Blender Benchmark 2.93.1GPU, classroom (CUDA) | 493.7 | 685.5 | reference |
| Blender Benchmark 2.90GPU, classroom (OPTIX) | 499.4 | 894.6 | reference |
| Blender Benchmark 2.91.2GPU, classroom (OPTIX) | 486.7 | — | no pair |
| Blender Benchmark 2.92GPU, classroom (OPTIX) | 472.9 | — | no pair |
| Blender Benchmark 2.93.1GPU, classroom (OPTIX) | 517.5 | — | no pair |
| Blender Benchmark 2.81GPU, fishy_cat (CUDA) | 324.2 | 511.3 | reference |
| Blender Benchmark 2.81aGPU, fishy_cat (CUDA) | 277.5 | 490.2 | reference |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 283.1 | 515.7 | reference |
| Blender Benchmark 2.83GPU, fishy_cat (CUDA) | 294.8 | 515.4 | reference |
| Blender Benchmark 2.90GPU, fishy_cat (CUDA) | 302 | 486.6 | reference |
| Blender Benchmark 2.90.1GPU, fishy_cat (CUDA) | 294.8 | — | no pair |
| Blender Benchmark 2.91.2GPU, fishy_cat (CUDA) | 289.1 | — | no pair |
| Blender Benchmark 2.92GPU, fishy_cat (CUDA) | 307.4 | 627.9 | reference |
| Blender Benchmark 2.93.1GPU, fishy_cat (CUDA) | 282.2 | 585.2 | reference |
| Blender Benchmark 2.90GPU, fishy_cat (OPTIX) | 253.8 | 567.7 | reference |
| Blender Benchmark 2.91.2GPU, fishy_cat (OPTIX) | 240.2 | — | no pair |
| Blender Benchmark 2.92GPU, fishy_cat (OPTIX) | 258.8 | — | no pair |
| Blender Benchmark 2.93.1GPU, fishy_cat (OPTIX) | 271.6 | — | no pair |
| Blender Benchmark 2.81aGPU, koro (CUDA) | 483 | 1,298.4 | reference |
| Blender Benchmark 2.82GPU, koro (CUDA) | 472.3 | 1,293.3 | reference |
| Blender Benchmark 2.83GPU, koro (CUDA) | 499.5 | 1,344.1 | reference |
| Blender Benchmark 2.90GPU, koro (CUDA) | 485.1 | 937.6 | reference |
| Blender Benchmark 2.90.1GPU, koro (CUDA) | 472.8 | — | no pair |
| Blender Benchmark 2.91.2GPU, koro (CUDA) | 457.8 | — | no pair |
| Blender Benchmark 2.92GPU, koro (CUDA) | 502.7 | 1,262.2 | reference |
| Blender Benchmark 2.93.1GPU, koro (CUDA) | 437.8 | 1,347.2 | reference |
| Blender Benchmark 2.90GPU, koro (OPTIX) | 319.9 | 671.3 | reference |
| Blender Benchmark 2.91.2GPU, koro (OPTIX) | 298 | — | no pair |
| Blender Benchmark 2.92GPU, koro (OPTIX) | 389.5 | — | no pair |
| Blender Benchmark 2.93.1GPU, koro (OPTIX) | 336.3 | — | no pair |
| Blender Benchmark 2.81GPU, pavillon_barcelona (CUDA) | 867.5 | 1,385.8 | reference |
| Blender Benchmark 2.81aGPU, pavillon_barcelona (CUDA) | 924.5 | 1,311.8 | reference |
| Blender Benchmark 2.82GPU, pavillon_barcelona (CUDA) | 894.6 | 1,315.1 | reference |
| Blender Benchmark 2.83GPU, pavillon_barcelona (CUDA) | 905.8 | 1,354.4 | reference |
| Blender Benchmark 2.90GPU, pavillon_barcelona (CUDA) | 942.6 | 1,294.8 | reference |
| Blender Benchmark 2.90.1GPU, pavillon_barcelona (CUDA) | 915.7 | — | no pair |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (CUDA) | 891.3 | — | no pair |
| Blender Benchmark 2.92GPU, pavillon_barcelona (CUDA) | 911 | 1,630.5 | reference |
| Blender Benchmark 2.93.1GPU, pavillon_barcelona (CUDA) | 796.1 | 1,131 | reference |
| Blender Benchmark 2.90GPU, pavillon_barcelona (OPTIX) | 722.4 | 1,474.4 | reference |
| Blender Benchmark 2.91.2GPU, pavillon_barcelona (OPTIX) | 702.6 | — | no pair |
| Blender Benchmark 2.92GPU, pavillon_barcelona (OPTIX) | 750.6 | — | no pair |
| Blender Benchmark 2.93.1GPU, pavillon_barcelona (OPTIX) | 753.6 | — | no pair |
| Blender Benchmark 2.81aGPU, victor (CUDA) | 1,360.8 | — | no pair |
| Blender Benchmark 2.82GPU, victor (CUDA) | 1,373 | — | no pair |
| Blender Benchmark 2.83GPU, victor (CUDA) | 1,376.7 | 5,823.8 | reference |
| Blender Benchmark 2.90GPU, victor (CUDA) | 1,426.6 | 5,116.6 | reference |
| Blender Benchmark 2.90.1GPU, victor (CUDA) | 1,215.8 | — | no pair |
| Blender Benchmark 2.91.2GPU, victor (CUDA) | 1,885.3 | — | no pair |
| Blender Benchmark 2.92GPU, victor (CUDA) | 1,640 | — | no pair |
| Blender Benchmark 2.93.1GPU, victor (CUDA) | 1,565.5 | — | no pair |
| Blender Benchmark 2.90GPU, victor (OPTIX) | 1,073.5 | — | no pair |
| Blender Benchmark 2.91.2GPU, victor (OPTIX) | 1,068 | — | no pair |
| Blender Benchmark 2.93.1GPU, victor (OPTIX) | 1,437.1 | — | no pair |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | 467.7 | — | no pair |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 457.1 | 153.4 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 454.8 | 245.5 | reference |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (CUDA) | 530.9 | — | no pair |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 497.2 | — | no pair |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 489.7 | 219 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 419.7 | — | no pair |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 528.8 | 203.2 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 522.7 | — | no pair |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 439.3 | — | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 501.2 | — | no pair |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 513.4 | — | no pair |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 498.5 | — | no pair |
| Blender Benchmark 4.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 438.5 | 186.5 | reference |
| Blender Benchmark 4.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 424 | 163.5 | reference |
| Blender Benchmark 5.1.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 391.6 | 144.8 | reference |
| Blender Benchmark 5.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 364.1 | 123.2 | reference |
| Blender Benchmark 3.0.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 508.8 | 179.6 | reference |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 474.7 | 180.9 | reference |
| Blender Benchmark 3.2.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 488.5 | — | no pair |
| Blender Benchmark 3.2.1GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 448.8 | 146 | reference |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 433.3 | 152.8 | reference |
| Blender Benchmark 3.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 429.7 | 172.9 | reference |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 470 | 184.1 | reference |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 476.8 | 178.6 | reference |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 428.9 | 169.6 | reference |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 429.3 | 160.6 | reference |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 442.7 | 184.4 | reference |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 428.4 | 144.2 | reference |
| Blender Benchmark 5.0.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 417 | — | no pair |
| Blender Benchmark 5.1.0GPU, sum of scenes monster + junkshop + classroom (OptiX / HIP / oneAPI / Metal) | 356.4 | — | no pair |
| Blender Benchmark 2.81GPU, classroom (CUDA) | — | 851.3 | no pair |
| Blender Benchmark 4.4.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 212.7 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
| Specification | A · GeForce GTX 1650 | B · GeForce GTX 960 | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | no data | GM206-300-A1 | no data for A |
| Architecture | Turing | Maxwell | differs |
| Shader unitsShader unit counts are comparable only within one architecture. | 896 (CUDA cores) | 1,024 (CUDA cores) | not directly comparable |
| Clocks | |||
| Base clock | 1,485 MHz | 1,127 MHz | A: 358 MHz more |
| Boost clockClocks of different architectures do not reflect performance directly. For laptop chips, the clock depends on the laptop’s power limit. | 1,665 MHz | 1,178 MHz | A: 487 MHz more |
| Memory | |||
| Video memory | 4 GB | 2 GB | A: 2 GB more |
| Memory type | GDDR5 | GDDR5 | equal |
| Memory bus | 128 bit | 128 bit | equal |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | no data | 112.2 GB/s | no data for A |
| 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. | 75 W (board power) | 120 W (TDP) | not directly comparable |
| Recommended PSU | 300 W | no data | no data for B |
| Interface | PCIe 3.0 | no data | no data for B |
| Length (reference / Founders Edition)Partner cards have different dimensions; check the specific SKU. | 130 mm | no data | no data for B |
| Thickness (slots) | 2 | no data | no data for B |
| Power connectors (reference) | 1x 6-pin | no data | no data for B |
Chip
GPU chip
Ano data
BGM206-300-A1
no data for AArchitecture
ATuring
BMaxwell
differsShader units
A896 (CUDA cores)
B1,024 (CUDA cores)
not directly comparableShader unit counts are comparable only within one architecture.
Clocks
Base clock
A1,485 MHz
B1,127 MHz
A: 358 MHz moreBoost clock
A1,665 MHz
B1,178 MHz
A: 487 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
A4 GB
B2 GB
A: 2 GB moreMemory type
AGDDR5
BGDDR5
equalMemory bus
A128 bit
B128 bit
equalMemory bandwidth
Ano data
B112.2 GB/s
no data for AExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A75 W (board power)
B120 W (TDP)
not directly comparableTGP (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
A300 W
Bno data
no data for BInterface
APCIe 3.0
Bno data
no data for BLength (reference / Founders Edition)
A130 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 6-pin
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 GTX 1650 and NVIDIA GeForce GTX 960 have?
NVIDIA GeForce GTX 1650: 4 GB GDDR5, 128-bit bus. NVIDIA GeForce GTX 960: 2 GB GDDR5, 128-bit bus.
Which is faster: NVIDIA GeForce GTX 1650 or NVIDIA GeForce GTX 960?
NVIDIA GeForce GTX 1650 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 GTX 1650checked November 7, 2026
- Wikipedia (English) — specifications of NVIDIA GeForce GTX 960, release date and launch pricechecked November 14, 2026
- Blender Open Data (Blender Foundation) — benchmark Blender Benchmark 2.81a, benchmark Blender Benchmark 2.81, benchmark Blender Benchmark 2.82, benchmark Blender Benchmark 2.83, 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 4.4.0, benchmark Blender Benchmark 5.1.1, benchmark Blender Benchmark 5.2.0, 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.