NVIDIA GeForce GTS 250 vs ATI Radeon HD 4870
Comparative analysis of NVIDIA GeForce GTS 250 and ATI Radeon HD 4870 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).
Differences
Reasons to consider the NVIDIA GeForce GTS 250
- Videocard is newer: launch date 8 month(s) later
- 2.4x more core clock speed: 1836 MHz vs 750 MHz
- Around 57% higher texture fill rate: 47.2 billion / sec vs 30 GTexel / s
- 2x more maximum memory size: 1 GB vs 512 MB
- Around 26% better performance in PassMark - G2D Mark: 54 vs 43
| Specifications (specs) | |
| Launch date | 4 March 2009 vs 25 June 2008 |
| Core clock speed | 1836 MHz vs 750 MHz |
| Texture fill rate | 47.2 billion / sec vs 30 GTexel / s |
| Maximum memory size | 1 GB vs 512 MB |
| Benchmarks | |
| PassMark - G2D Mark | 54 vs 43 |
| GFXBench 4.0 - T-Rex (Frames) | 3351 vs 3346 |
| GFXBench 4.0 - T-Rex (Fps) | 3351 vs 3346 |
Reasons to consider the ATI Radeon HD 4870
- 6.3x more pipelines: 800 vs 128
- 3.1x better floating-point performance: 1,200.0 gflops vs 387.1 gflops
- 3.3x more memory clock speed: 3600 MHz vs 1100 MHz
- 2.3x better performance in PassMark - G3D Mark: 1386 vs 591
| Specifications (specs) | |
| Pipelines | 800 vs 128 |
| Floating-point performance | 1,200.0 gflops vs 387.1 gflops |
| Memory clock speed | 3600 MHz vs 1100 MHz |
| Benchmarks | |
| PassMark - G3D Mark | 1386 vs 591 |
Compare benchmarks
GPU 1: NVIDIA GeForce GTS 250
GPU 2: ATI Radeon HD 4870
| PassMark - G3D Mark |
|
|
||||
| PassMark - G2D Mark |
|
|
||||
| GFXBench 4.0 - T-Rex (Frames) |
|
|
||||
| GFXBench 4.0 - T-Rex (Fps) |
|
|
| Name | NVIDIA GeForce GTS 250 | ATI Radeon HD 4870 |
|---|---|---|
| PassMark - G3D Mark | 591 | 1386 |
| PassMark - G2D Mark | 54 | 43 |
| GFXBench 4.0 - Manhattan (Frames) | 3108 | |
| GFXBench 4.0 - Manhattan (Fps) | 3108 | |
| GFXBench 4.0 - T-Rex (Frames) | 3351 | 3346 |
| GFXBench 4.0 - T-Rex (Fps) | 3351 | 3346 |
Compare specifications (specs)
| NVIDIA GeForce GTS 250 | ATI Radeon HD 4870 | |
|---|---|---|
Essentials |
||
| Architecture | Tesla | TeraScale |
| Code name | G92B | RV770 |
| Launch date | 4 March 2009 | 25 June 2008 |
| Launch price (MSRP) | $199 | $299 |
| Place in performance rating | 1021 | 1329 |
| Price now | $114.99 | |
| Type | Desktop | Desktop |
| Value for money (0-100) | 9.91 | |
Technical info |
||
| Core clock speed | 1836 MHz | 750 MHz |
| CUDA cores | 128 | |
| Floating-point performance | 387.1 gflops | 1,200.0 gflops |
| Manufacturing process technology | 55 nm | 55 nm |
| Maximum GPU temperature | 105 °C | |
| Pipelines | 128 | 800 |
| Texture fill rate | 47.2 billion / sec | 30 GTexel / s |
| Thermal Design Power (TDP) | 150 Watt | 150 Watt |
| Transistor count | 754 million | 956 million |
Video outputs and ports |
||
| Audio input for HDMI | S / PDIF | |
| Display Connectors | 2x DVI, Two Dual Link DVI | 2x DVI, 1x S-Video |
| HDMI | ||
| Maximum VGA resolution | 2048x1536 | |
| Multi monitor support | ||
Compatibility, dimensions and requirements |
||
| Height | 4.376" (111 mm) (11.1 cm) | |
| Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Length | 9" (228.6 mm) (22.9 cm) | 250 mm |
| SLI options | 2-way3-way | |
| Supplementary power connectors | 6-pin | 2x 6-pin |
API support |
||
| DirectX | 10.0 | 10.1 |
| OpenGL | 3.0 | 3.3 |
Memory |
||
| Maximum RAM amount | 1 GB | 512 MB |
| Memory bandwidth | 70.4 GB / s | 115.2 GB / s |
| Memory bus width | 256 Bit | 256 Bit |
| Memory clock speed | 1100 MHz | 3600 MHz |
| Memory type | GDDR3 | GDDR5 |
Technologies |
||
| 3D Vision | ||
| CUDA | ||
| SLI | ||
