GeForce 920M vs GeForce GTX 870M: specs and benchmark comparison
Short verdict
Not enough data for a performance conclusion: the database has no comparable benchmarks for this pair. Below are the key differences in official specifications.
Compare with AIAdvantages
Only measured and rated values: a noticeable benchmark gap and specs where more is better.
Where GeForce 920M is better1
Board power 77 W lower33 W (TDP) vs 110 W (TDP)
Where GeForce GTX 870M is better2
Memory bus 128 bit more192 bit vs 64 bit
Memory bandwidth 105.6 GB/s more120 GB/s vs 14.4 GB/s
Benchmarks
Results are compared within one benchmark, one version and the same conditions. Laptop chip results depend on the laptop model: its maker sets the power limit and cooling.
Blender Benchmark 2.81a
GPU, bmw27 (CUDA) · s, lower is better
GeForce 920M1,061.6 sGeForce GTX 870M326.9 sNo advantage conclusion: small sample in one of the results.
About the measurement and source
- A · NVIDIA GeForce 920M
1,061.6 s · community measurement, sample 1 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 1 submissions (0 outliers excluded), interquartile range 1061.64–1061.64; submissions 2020-01-23 to 2020-01-23; CUDA backend. Snapshot 2026-11-14.
- B · NVIDIA GeForce GTX 870M
326.9 s · community measurement, sample 1 · November 14, 2026
Blender Open Data (Blender Foundation)
Median of 1 submissions (0 outliers excluded), interquartile range 326.86–326.86; submissions 2020-01-25 to 2020-01-25; 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 (15)
| Benchmark | A | B | Difference |
|---|---|---|---|
| Blender Benchmark 2.82GPU, bmw27 (CUDA) | 1,105 | — | no pair |
| Blender Benchmark 2.83GPU, bmw27 (CUDA) | 1,045 | — | no pair |
| Blender Benchmark 2.90GPU, bmw27 (CUDA) | 1,090.7 | — | no pair |
| Blender Benchmark 2.91.2GPU, bmw27 (CUDA) | 1,444.6 | — | no pair |
| Blender Benchmark 2.81GPU, classroom (CUDA) | 3,615.7 | — | no pair |
| Blender Benchmark 2.90GPU, classroom (CUDA) | 3,609.6 | — | no pair |
| Blender Benchmark 2.82GPU, fishy_cat (CUDA) | 2,154.4 | — | no pair |
| Blender Benchmark 3.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 49.8 | — | no pair |
| Blender Benchmark 3.6.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 47.1 | — | no pair |
| Blender Benchmark 4.0.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 45.2 | — | no pair |
| Blender Benchmark 4.1.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | 36.6 | — | no pair |
| Blender Benchmark 2.81aGPU, classroom (CUDA) | — | 1,130 | no pair |
| Blender Benchmark 3.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 156 | no pair |
| Blender Benchmark 3.5.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 150.8 | no pair |
| Blender Benchmark 4.3.0GPU, sum of scenes monster + junkshop + classroom (CUDA) | — | 120.1 | no pair |
Each benchmark version has its own scale: numbers are compared only within a row.
Specifications
Chip maker values. The laptop maker sets the power limit and clocks in each laptop.
| Specification | A · GeForce 920M | B · GeForce GTX 870M | Difference |
|---|---|---|---|
| Chip | |||
| GPU chip | GK208 | GK104 | differs |
| Architecture | Kepler | Kepler | equal |
| Memory | |||
| Video memory | 2 GB | no data | no data for B |
| Memory type | DDR3 | GDDR5 | differs |
| Memory bus | 64 bit | 192 bit | B: 128 bit more |
| Memory bandwidthExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently. | 14.4 GB/s | 120 GB/s | B: 105.6 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. | 33 W (TDP) | 110 W (TDP) | B: 77 W higher |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 | equal |
Chip
GPU chip
AGK208
BGK104
differsArchitecture
AKepler
BKepler
equal
Memory
Video memory
A2 GB
Bno data
no data for BMemory type
ADDR3
BGDDR5
differsMemory bus
A64 bit
B192 bit
B: 128 bit moreMemory bandwidth
A14.4 GB/s
B120 GB/s
B: 105.6 GB/s moreExcludes cache (Infinity Cache / L2), which affects effective bandwidth differently.
Power and dimensions
Board power
A33 W (TDP)
B110 W (TDP)
B: 77 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.
Interface
APCIe 3.0 x16
BPCIe 3.0 x16
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
Which PCIe interface do the cards use?
NVIDIA GeForce 920M: PCIe 3.0 x16. NVIDIA GeForce GTX 870M: PCIe 3.0 x16.
See also
Data sources (2)
- Wikipedia (English) — specifications of NVIDIA GeForce 920M, specifications of NVIDIA GeForce GTX 870M, release date and launch pricechecked November 14, 2026
- Blender Open Data (Blender Foundation) — 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 2.81, benchmark Blender Benchmark 3.1.0, benchmark Blender Benchmark 3.6.0, benchmark Blender Benchmark 4.0.0, benchmark Blender Benchmark 4.1.0, benchmark Blender Benchmark 3.3.0, benchmark Blender Benchmark 3.5.0, benchmark Blender Benchmark 4.3.0checked November 14, 2026
How we compare: methodology. Where the data comes from: sources.