GeForce RTX 3070 vs GeForce GTX 660
GeForce RTX 3070
Popular choices:
GeForce GTX 660
Popular choices:
Performance Spectrum - GPU
About G3D Mark
G3D Mark is a standard benchmark that measures graphics performance in real-world gaming scenarios. It simplifies comparing cards from different brands, where higher scores directly correlate with better fps and smoother gaming experiences.
Value Upgrade Path
This is the official ChipVERSUS Value Rating, comparing raw performance (G3D Mark) per dollar. Components placed above yours deliver better value for money.
Avg price is the current average price collected from markets across the web.
Performance Per Dollar GeForce RTX 3070
Performance Per Dollar
Performance Comparison
About G3D Mark🏆 Chipversus Verdict
⚠️ Generational Difference
The GeForce RTX 3070 is significantly newer (2020 vs 2012). The GeForce RTX 3070 likely supports modern features like Ray Tracing, Tensor Cores, and DLSS/FSR upscaling, which act as force multipliers for performance. The GeForce GTX 660 lacks this hardware feature set, limiting its longevity in modern titles despite any raw power similarities.
🚀 Performance Leadership
The GeForce RTX 3070 is the superior choice for raw performance. It leads with a 448.8% higher G3D Mark score and 166.7% more VRAM (8 GB vs 3 GB). This advantage makes it significantly better for higher resolutions (1440p/4K) and graphic-intensive titles compared to the GeForce GTX 660.
| Insight | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| Performance | ✅Leading raw performance (+448.8%) | ❌Lower raw frame rates (-448.8%) |
| Longevity | 🔮Strong Longevity (Ampere (2020−2025) / 8nm) | 🛑Obsolete Architecture (2012 / Kepler (2012−2018)) |
| Ecosystem | ✨ DLSS 2 Upscaling | Supports FSR Upscaling |
| VRAM | 🎮 High Capacity (8 GB) | ❌ Less VRAM capacity |
| Efficiency | 💡 Excellent Perf/Watt | ⚡ Higher Power Consumption |
| Case Fit | 📏 Compact / SFF Friendly | 📏 Compact / SFF Friendly |
💎 Value Proposition
The GeForce GTX 660 offers a compelling cost-to-performance ratio. Priced at $15 versus $200 for the GeForce RTX 3070, it costs 93% less. While it maintains significantly lower raw performance, this results in a 142.9% higher cost efficiency score.
| Insight | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| Cost Efficiency | ❌Lower cost efficiency | ✅Better overall value (+142.9%) |
| Upfront Cost | ⚠️Higher upfront cost ($200) | ✅More affordable ($15) |
Performance Check
Real-world benchmarks and performance projections based on comprehensive hardware analysis and comparative metrics. Values represent expected performance on High/Ultra settings at 1080p, 1440p, and 4K. Modeled using a Ryzen 7 7800X3D reference profile to minimize specific CPU bottlenecks.
Note: Performance behavior can vary per game. Specific architectures may perform better or worse depending on game engine optimizations and API implementation.
Technical Specifications
Side-by-side comparison of GeForce RTX 3070 and GeForce GTX 660
GeForce RTX 3070
The GeForce RTX 3070 is manufactured by NVIDIA. It was released in September 1 2020. It features the Ampere architecture. The core clock ranges from 1500 MHz to 1725 MHz. It has 5888 shading units. The thermal design power (TDP) is 220W. Manufactured using 8 nm process technology. It features 46 dedicated ray tracing cores for enhanced lighting effects. G3D Mark benchmark score: 22,172 points. Launch price was $499.
GeForce GTX 660
The GeForce GTX 660 is manufactured by NVIDIA. It was released in September 6 2012. It features the Kepler architecture. The core clock ranges from 980 MHz to 1033 MHz. It has 960 shading units. The thermal design power (TDP) is 140W. Manufactured using 28 nm process technology. G3D Mark benchmark score: 4,040 points. Launch price was $229.
Graphics Performance
In G3D Mark, the GeForce RTX 3070 scores 22,172 versus the GeForce GTX 660's 4,040 — the GeForce RTX 3070 leads by 448.8%. The GeForce RTX 3070 is built on Ampere while the GeForce GTX 660 uses Kepler, both on 8 nm vs 28 nm. Shader units: 5,888 (GeForce RTX 3070) vs 960 (GeForce GTX 660). Raw compute: 20.31 TFLOPS (GeForce RTX 3070) vs 1.981 TFLOPS (GeForce GTX 660). Boost clocks: 1725 MHz vs 1033 MHz.
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| G3D Mark Score | 22,172+449% | 4,040 |
| Architecture | Ampere | Kepler |
| Process Node | 8 nm | 28 nm |
| Shading Units | 5888+513% | 960 |
| Compute (TFLOPS) | 20.31 TFLOPS+925% | 1.981 TFLOPS |
| Boost Clock | 1725 MHz+67% | 1033 MHz |
| ROPs | 96+300% | 24 |
| TMUs | 184+130% | 80 |
| L1 Cache | 5.8 MB+7150% | 0.08 MB |
| L2 Cache | 4 MB+953% | 0.38 MB |
Advanced Features (DLSS/FSR)
The GeForce RTX 3070 gives access to NVIDIA DLSS (Deep Learning Super Sampling), widely regarding as the superior upscaling method for image quality. The GeForce GTX 660 relies on FSR (FidelityFX Super Resolution), which is capable but generally slightly noisier than DLSS in motion.
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| Upscaling Tech | DLSS 2.0 | FSR 2.1 (Compatible) |
| Frame Generation | FSR 3 / AFMF (Compatible) | FSR 3 (Compatible) |
| Ray Reconstruction | No | No |
| Low Latency | NVIDIA Reflex | Standard |
Video Memory (VRAM)
The GeForce RTX 3070 comes with 8 GB of VRAM, while the GeForce GTX 660 has 3 GB. The GeForce RTX 3070 offers 166.7% more capacity, crucial for higher resolutions and texture-heavy games. Memory bandwidth: 448 GB/s (GeForce RTX 3070) vs 144.2 GB/s (GeForce GTX 660) — a 210.7% advantage for the GeForce RTX 3070. Bus width: 256-bit vs 192-bit. L2 Cache: 4 MB (GeForce RTX 3070) vs 0.38 MB (GeForce GTX 660) — the GeForce RTX 3070 has significantly larger on-die cache to reduce VRAM reliance.
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| VRAM Capacity | 8 GB+167% | 3 GB |
| Memory Type | GDDR6 | GDDR5 |
| Memory Bandwidth | 448 GB/s+211% | 144.2 GB/s |
| Bus Width | 256-bit+33% | 192-bit |
| L2 Cache | 4 MB+953% | 0.38 MB |
Display & API Support
DirectX support: 12 Ultimate (GeForce RTX 3070) vs 12 (GeForce GTX 660). Maximum simultaneous displays: 4 vs 4.
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| DirectX | 12 Ultimate | 12 |
| Max Displays | 4 | 4 |
Media & Encoding
Hardware encoder: NVENC 7th gen (GeForce RTX 3070) vs NVENC 1st Gen (GeForce GTX 660). Decoder: NVDEC 5th gen vs NVDEC 1st Gen. Supported codecs: H.264,H.265/HEVC,AV1,VP9 (GeForce RTX 3070) vs H.264 (GeForce GTX 660).
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| Encoder | NVENC 7th gen | NVENC 1st Gen |
| Decoder | NVDEC 5th gen | NVDEC 1st Gen |
| Codecs | H.264,H.265/HEVC,AV1,VP9 | H.264 |
Power & Dimensions
The GeForce RTX 3070 draws 220W versus the GeForce GTX 660's 140W — a 44.4% difference. The GeForce GTX 660 is more power-efficient. Recommended PSU: 650W (GeForce RTX 3070) vs 450W (GeForce GTX 660). Power connectors: 8-pin vs 1x 6-pin. Card length: 242mm vs 241mm, occupying 2 vs 2 slots.
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| TDP | 220W | 140W-36% |
| Recommended PSU | 650W | 450W-31% |
| Power Connector | 8-pin | 1x 6-pin |
| Length | 242mm | 241mm |
| Height | 112mm | — |
| Slots | 2 | 2 |
| Temp (Load) | 75°C | — |
| Perf/Watt | 100.8+249% | 28.9 |
Value Analysis
The GeForce RTX 3070 launched at $499 MSRP and currently averages $200, while the GeForce GTX 660 launched at $229 and now averages $15. The GeForce GTX 660 costs 92.5% less ($185 savings) at current market prices. Performance per dollar (G3D Mark / price): 110.9 (GeForce RTX 3070) vs 269.3 (GeForce GTX 660) — the GeForce GTX 660 offers 142.8% better value. The GeForce RTX 3070 is the newer GPU (2020 vs 2012).
| Feature | GeForce RTX 3070 | GeForce GTX 660 |
|---|---|---|
| MSRP | $499 | $229-54% |
| Avg Price (30d) | $200 | $15-93% |
| Performance per Dollar | 110.9 | 269.3+143% |
| Codename | GA104 | GK106 |
| Release | September 1 2020 | September 6 2012 |
| Ranking | #63 | #490 |
Top Performing GPUs
The most powerful gpus ranked by G3D Mark benchmark scores.
You May Also Compare
Similar GPU comparisons based on GeForce RTX 3070 and GeForce GTX 660
