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.

GeForce GTX 660 vs GeForce RTX 3070 FPS Benchmarks

Predicted gaming performance across popular games. Tested paired with Ryzen 7 9800X3D to isolate GPU performance.

Search any supported game below to compare 1080p FPS for both components.

GeForce GTX 660 vs GeForce RTX 3070: Pros, Cons & Final Verdict

See where each GPU makes more sense in practice: raw FPS, VRAM, features, power draw, pricing, and long-term headroom.

GeForce GTX 660

2012

Why buy it

✅Costs $270 less on MSRP ($229 MSRP vs $499 MSRP).
✅Draws 140W instead of 220W, a 80W reduction.
✅Measures 241mm instead of 242mm, a 1mm shorter card that is more SFF-friendly.

Trade-offs

❌Lower average FPS than GeForce RTX 3070 across 50 tracked games in our benchmark data.
❌Less VRAM, with 3 GB vs 8 GB for high-resolution textures and newer games.
❌No DLSS support; it relies on Upscaling support instead.
❌2012 hardware with 3 GB of VRAM is already well past its comfortable zone for modern gaming, so it is hard to recommend now.
❌Lower G3D Mark per dollar, at 17.6 vs 44.4 G3D/$ ($229 MSRP vs $499 MSRP).

GeForce RTX 3070

2020

Why buy it

✅515.7% more average FPS across 50 tracked games in our benchmark data.
✅Delivers 151.9% more G3D Mark for each dollar spent, at 44.4 vs 17.6 G3D/$ ($499 MSRP vs $229 MSRP).
✅Access to DLSS 2 Super Resolution (2020).
✅166.7% more VRAM for high-resolution textures and newer games (8 GB vs 3 GB).
✅Better long-term bet: Ampere (2020−2025) on 8nm gives it a newer hardware base for upcoming games.

Trade-offs

❌57.1% higher power demand at 220W vs 140W.

Quick Answers

Which GPU is faster for gaming right now?

GeForce RTX 3070 is the faster gaming card right now. In our data, it leads by 515.7% in average FPS across 50 tracked games in our benchmark data and by 448.8% in PassMark G3D (22,172 vs 4,040), so the answer here is pretty clean.

Which GPU is the safer long-term pick for 2026 and beyond?

GeForce RTX 3070 is the safer long-term pick for 2026 and beyond. The case is simple: 8 GB vs 3 GB of VRAM, the newer upscaling stack, DLSS 2 Super Resolution (2020) instead of no meaningful modern upscaling stack, a 8nm process instead of 28nm, and 46 vs 0 ray-tracing units. That gives it more room for heavier textures and higher settings over time.

Which GPU is the better buy today?

GeForce RTX 3070 makes the most sense to buy today. It is $270 more expensive on MSRP at $499 vs $229, and it leads G3D-per-dollar by 151.9% (44.4 vs 17.6), so the value case lines up with the gaming result.

GeForce GTX 660 vs GeForce RTX 3070 Technical Specifications

Side-by-side specs, architecture details, clocks, memory, power, and platform differences.

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.

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.

⚡

Graphics Performance

In G3D Mark, the GeForce GTX 660 scores 4,040 versus the GeForce RTX 3070's 22,172 — the GeForce RTX 3070 leads by 448.8%. The GeForce GTX 660 is built on Kepler while the GeForce RTX 3070 uses Ampere, both on 28 nm vs 8 nm. Shader units: 960 (GeForce GTX 660) vs 5,888 (GeForce RTX 3070). Raw compute: 1.981 TFLOPS (GeForce GTX 660) vs 20.31 TFLOPS (GeForce RTX 3070). Boost clocks: 1033 MHz vs 1725 MHz.

Feature	GeForce GTX 660	GeForce RTX 3070
G3D Mark Score	4,040	22,172+449%
Architecture	Kepler	Ampere
Process Node	28 nm	8 nm
Shading Units	960	5888+513%
Compute (TFLOPS)	1.981 TFLOPS	20.31 TFLOPS+925%
Boost Clock	1033 MHz	1725 MHz+67%
ROPs	24	96+300%
TMUs	80	184+130%
L1 Cache	0.08 MB	5.8 MB+7150%
L2 Cache	0.38 MB	4 MB+953%

✨

Advanced Features (DLSS/FSR)

The GeForce RTX 3070 supports the newer DLSS 2 Super Resolution, whereas the GeForce GTX 660 is capped at Upscaling support.

Feature	GeForce GTX 660	GeForce RTX 3070
Upscaling Tech	Upscaling support	DLSS 2 Super Resolution
Frame Generation	Not Supported	Not Supported
Ray Reconstruction	No	No
Low Latency	NVIDIA Reflex	NVIDIA Reflex

💾

Video Memory (VRAM)

The GeForce GTX 660 has 3 GB of VRAM, while the GeForce RTX 3070 carries 8 GB. GeForce RTX 3070 gives you 166.7% more memory capacity, which matters more once you move into heavier textures, mods, or higher resolutions. Memory bandwidth: 144.2 GB/s (GeForce GTX 660) vs 448 GB/s (GeForce RTX 3070) — a 210.7% advantage for the GeForce RTX 3070. Memory bus width is 192-bit on the GeForce GTX 660 and 256-bit on the GeForce RTX 3070. L2 Cache: 0.38 MB (GeForce GTX 660) vs 4 MB (GeForce RTX 3070) — the GeForce RTX 3070 has significantly larger on-die cache to reduce VRAM reliance.

Feature	GeForce GTX 660	GeForce RTX 3070
VRAM Capacity	3 GB	8 GB+167%
Memory Type	GDDR5	GDDR6
Memory Bandwidth	144.2 GB/s	448 GB/s+211%
Bus Width	192-bit	256-bit+33%
L2 Cache	0.38 MB	4 MB+953%

🖥️

Display & API Support

DirectX support: 12 (GeForce GTX 660) vs 12 Ultimate (GeForce RTX 3070). Maximum simultaneous displays: 4 vs 4.

Feature	GeForce GTX 660	GeForce RTX 3070
DirectX	12	12 Ultimate
Max Displays	4	4

🎬

Media & Encoding

Hardware encoder: NVENC 1st Gen (GeForce GTX 660) vs NVENC 7th gen (GeForce RTX 3070). Decoder: NVDEC 1st Gen vs NVDEC 5th gen. Supported codecs: H.264 (GeForce GTX 660) vs H.264,H.265/HEVC,AV1,VP9 (GeForce RTX 3070).

Feature	GeForce GTX 660	GeForce RTX 3070
Encoder	NVENC 1st Gen	NVENC 7th gen
Decoder	NVDEC 1st Gen	NVDEC 5th gen
Codecs	H.264	H.264,H.265/HEVC,AV1,VP9

🔌

Power & Dimensions

The GeForce GTX 660 draws 140W versus the GeForce RTX 3070's 220W — a 44.4% difference. The GeForce GTX 660 is more power-efficient. Recommended PSU: 450W (GeForce GTX 660) vs 650W (GeForce RTX 3070). Power connectors: 1x 6-pin vs 8-pin. Card length: 241mm vs 242mm, occupying 2 vs 2 slots.

Feature	GeForce GTX 660	GeForce RTX 3070
TDP	140W-36%	220W
Recommended PSU	450W-31%	650W
Power Connector	1x 6-pin	8-pin
Length	241mm	242mm
Height	—	112mm
Slots	2	2
Temp (Load)	—	75°C
Perf/Watt	28.9	100.8+249%

💰

Value Analysis

At launch, the GeForce GTX 660 came in at $229, while the GeForce RTX 3070 launched at $499. On MSRP, GeForce GTX 660 was 54.1% cheaper ($270 less). Performance per dollar on MSRP (G3D Mark / MSRP): 17.6 (GeForce GTX 660) vs 44.4 (GeForce RTX 3070) — the GeForce RTX 3070 offers 152.3% better value. The newer card here is GeForce RTX 3070 (2020 vs 2012).

Feature	GeForce GTX 660	GeForce RTX 3070
MSRP	$229-54%	$499
Performance per Dollar	17.6	44.4+152%
Codename	GK106	GA104
Release	September 6 2012	September 1 2020
Ranking	#490	#63

Search GeForce GTX 660 on Amazon

Search GeForce RTX 3070 on Amazon

Affiliate Disclosure

ChipVERSUS is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com. We may earn a commission on qualifying purchases made through our links. This comes at no additional cost to you and helps support our work in providing comprehensive PC building guides and tools.

Amazon and the Amazon logo are trademarks of Amazon.com, Inc. or its affiliates.