RTX 2060 vs GTX 1080
The complete head-to-head: full specs, real per-game FPS with 1% lows, ray tracing, a live CPU-bottleneck check, thermals, power and value, with a straight verdict.
GeForce RTX 2060

GeForce GTX 1080

avg, 1080p
The short answer
This is one of the closest cross-generation matchups on this site. The RTX 2060 is only about 6% faster on average, close enough that it comes down to features and price rather than raw speed. The 2060 adds RT cores and DLSS, runs 20 W cooler, and costs noticeably less on the used market. The GTX 1080 answers back with 8 GB of VRAM against 6 GB and a 256-bit bus, plus it was a genuine flagship in 2016 that still holds its own. If the performance gap were bigger, this would be an easy call. It isn't, so weigh VRAM and features, not speed.
The RTX 2060 launched in 2019 to essentially match a card that had been a $599 flagship three years earlier, and that comparison still holds up in 2026. These two trade blows: the 2060 is a hair faster and adds ray tracing and DLSS, the 1080 answers with more memory and a wider bus. Neither side wins outright, which is unusual for a matchup on this site.
With a gap this small, the numbers below, frame-by-frame benchmarks, thermal and power draw, VRAM behavior once texture packs stack up, and used pricing, do more to settle this than the 6% headline figure ever could.
At a glance
Seven dimensions, two cards. Bigger area is not automatically better, each card owns different corners.
Strengths radar
Each axis scored 0-100 relative to the pair
Performance vs price
Up and to the left is better value
Grey dots are neighbouring cards for context.
Which should you buy?
Pick your use case, the winner changes with what you actually do.
A hair faster, cooler, and DLSS gives it more room to grow into future titles than the 1080 has.
8 GB on a 256-bit bus is the more comfortable setup once texture packs and 1440p settings stack up.
Tensor cores accelerate AI workloads directly, something the 1080's extra 2 GB cannot substitute for.
Turing's NVENC adds HEVC B-frame support that Pascal's encoder in the 1080 doesn't have.
160 W against 180 W isn't a huge gap, but the 2060 is the easier fit for a tighter PSU or case.
8 GB of headroom plus a close 320 GB/s of bandwidth make the 1080 the steadier pick for high-res emulation.
Already own a GTX 1080? Skip the 2060, it's a sidegrade at best.
Short answer: probably not
A 6% average gain is not worth losing 2 GB of VRAM for. You'd mainly be buying RT cores and DLSS, which only matter if you plan to actually use them, plus a somewhat newer encoder if you stream.
If you already own a 1080, either keep it or jump further ahead to a used RTX 3060, which is a clear step up in speed, VRAM, and DLSS performance over both of these cards, not just a lateral move.
Full specification comparison
Every spec side by side. The highlighted figure wins each row.
| Specification | RTX 2060 | GTX 1080 |
|---|---|---|
| Architecture | ||
| GPU / architecture | TU106-200A · Turing | GP104-400 · Pascal |
| Process node | TSMC 12nm FFN ▲ | TSMC 16nm FinFET |
| Release date | Jan 15, 2019 | May 27, 2016 |
| Launch MSRP | $349 ▲ | $599 |
| Compute | ||
| CUDA cores | 1,920 | 2,560 ▲ |
| RT cores | 30 · 1st gen ▲ | None |
| Tensor cores | 240 · 1st gen ▲ | None |
| Base / boost clock | 1365 / 1680 MHz | 1607 / 1733 MHz ▲ |
| L2 cache | 3 MB ▲ | 2 MB |
| Memory | ||
| VRAM | 6 GB GDDR6 | 8 GB GDDR5X ▲ |
| Memory bus | 192-bit | 256-bit ▲ |
| Bandwidth | 336 GB/s ▲ | 320 GB/s |
| Power & form factor | ||
| TDP | 160 W ▲ | 180 W |
| Power connector | 1× 8-pin | 1× 8-pin |
| Suggested PSU | 500 W ▲ | 550 W |
| PCIe interface | 3.0 ×16 | 3.0 ×16 |
| Features | ||
| Upscaling | DLSS 2 / Super Res + FSR ▲ | FSR / NIS only, no DLSS |
| AV1 encode (NVENC) | No | No |
| Display outputs | 3×DP1.4 · HDMI 2.0b | 3×DP1.4 · HDMI 2.0b · DVI-D |
Average FPS by game
Switch resolution, metric, ray tracing and upscaling, the bars update live. Hover a bar for the avg / 1% / 0.1% breakdown.
Average FPS · 1080p · Rasterization. Representative data, hover a bar for avg / 1% / 0.1%. Note the GTX 1080's 1% lows fall off at 1440p and up from its 8 GB VRAM.
Smoothness & frametimes
Average FPS hides stutter. This is one run plotted as frametime, a flat line is smooth, spikes are hitches. Watch what the GTX 1080's 8 GB VRAM does in a texture-heavy game.
Frametime: Alan Wake 2, 1080p Ultra
Lower and flatter is better · 16.7 ms = 60 fps
Counterintuitive but real: the slower RTX 2060 delivers a smoother line here because 12 GB holds the texture pool the 8 GB GTX 1080 keeps evicting, those spikes are VRAM stutter, not raw speed.
Lab scores
Clean apples-to-apples tests, useful, but weaker at predicting real games than the FPS above.
Ray tracing & upscaling
Ray tracing tanks both cards at native resolution. What makes it playable is upscaling, and here the GTX 1080 has a real edge.
Is frame generation "real" performance?
Frame Generation in DLSS 3 needs the Optical Flow Accelerator that only showed up with RTX 40-series silicon, so neither of these older cards has it. The RTX 2060 can still do Super Resolution upscaling through its Tensor cores, but the GTX 1080 came out three years before Tensor cores existed on a GeForce card, so it has no DLSS of any kind, upscaling included.
AMD's FSR 3 Frame Generation works on both since it isn't tied to specific hardware. It's the only frame-gen path either card has, useful in single-player games, best avoided in competitive titles or below roughly 50 base fps.
Will your CPU bottleneck these cards?
A faster GPU only helps if your CPU keeps up. Pick your CPU and resolution to see expected FPS and bottleneck for each card.
CPU + GPU pairing check
The willitbottleneck engine, built right into the comparison.
Estimated from a 43-CPU model across 1440p. A weak CPU mostly bites at 1080p; at higher resolutions the GPU becomes the limiter and the bottleneck shrinks.
Thermals & noise
The efficiency gap shows up here: the newer card runs cooler and quieter, day in and day out.
Real draw, efficiency & PSU
TDP is the rated figure; what matters is real gaming draw and how many frames you get per watt.
Both use a single 8-pin connector. If your PSU already ran the RTX 2060, it will run the GTX 1080 easily. Leave about 30% headroom for spikes.
Will it fit, and what to pair it with?
Size to scale
Card length matters for small cases
What monitor to pair
Both land in the same range given how close they are: 1080p at 100-144 Hz comfortably, and 1440p at 60 Hz achievable on either with settings dialed back. The RTX 2060 has a bit more headroom thanks to DLSS in supported titles.
Running an older PCIe 3.0 board?
The 2060 and the 1080 both use a PCIe 3.0 ×16 connection, so this is a non-factor between the two of them. Neither card gets anywhere close to saturating even a 3.0 ×8 link, which is why both still perform identically to their launch-day numbers when dropped into a current PCIe 4.0 or 5.0 motherboard.
Price history & dollars-per-frame
Raw price is only half the story. Cost per frame is the number that decides it, and it keeps moving as prices fall.
New price over time
Street price of new cards (USD)
The 6 GB vs 8 GB question
RTX 2060 · 6 GB
- 336 GB/s of bandwidth, slightly ahead of the 1080's 320 GB/s, keeps the smaller pool from feeling as tight as the raw number suggests.
- Tensor cores make local AI tools that fit in 6 GB noticeably faster than the 1080's memory-only advantage buys it.
- 6 GB is the tighter fit for 1440p or heavily modded games, where the 1080's 8 GB has real breathing room.
- Since the two are close in raw speed, the 1080's extra VRAM becomes the deciding factor for a lot of buyers.
GTX 1080 · 8 GB
- 8 GB on a 256-bit bus is comfortable for 1080p and reasonable for 1440p even by 2026 standards.
- Extra capacity helps most in emulation and in games with large, uncompressed texture packs.
- 320 GB/s of bandwidth is slightly behind the 2060's 336 GB/s, so the extra capacity doesn't fully translate into extra speed.
- No Tensor cores at all, so there's no DLSS fallback if 8 GB ever does run short.
Emulation & memory bandwidth
The narrower bus is a real downgrade for emulation
This one leans toward the GTX 1080. Its 8 GB and 320 GB/s of bandwidth are both close to or ahead of what many emulator cores need at high internal resolutions, and the extra capacity avoids the hard stutter that comes from running out of VRAM entirely. The RTX 2060's slight bandwidth edge, 336 GB/s against 320 GB/s, doesn't make up for having 2 GB less to work with once texture packs get involved.
Creator, AI & streaming
The newer card is quicker per task, but the older card's extra VRAM unlocks larger jobs it can't fit at all.
Streaming: the AV1 encoder is the differentiator
The RTX 2060 has the newer NVENC implementation. Turing added HEVC B-frame support that Pascal's encoder in the GTX 1080 lacks, a real, visible improvement in quality at the same bitrate. Neither card has an AV1 encoder, that arrived with Ada Lovelace.
Overclocking & undervolting
Pascal has real overclocking headroom on the GTX 1080, often 10-15% with a decent cooler, enough to pull ahead of a stock RTX 2060 outright. The 2060 has less room to give, 5-8% typically, so undervolting is the better use of time there.
Pros & cons
RTX 2060
- RT cores and Tensor cores for DLSS, the 1080 has neither
- Runs 20 W cooler and costs meaningfully less used
- Newer NVENC encoder with HEVC B-frame support
- 6 GB VRAM against the 1080's 8 GB
- Only about 6% faster on average, a close race
GTX 1080
- 8 GB VRAM on a wide 256-bit bus
- More CUDA cores and higher clocks out of the box
- Strong overclocking headroom, often 10-15%
- No RT cores or DLSS, stuck with FSR/NIS upscaling
- Runs hotter and louder, 180 W against 160 W
- Costs more used for barely less speed than the 2060
Buying pitfalls
Which RTX 2060 are you buying?
A rare 2021 re-release used a 12 GB GDDR6 configuration with 2,176 CUDA cores instead of the original 1,920-core, 6 GB card. That variant closes most of the VRAM gap this page is built around, so check the box or a GPU-Z readout before buying used.
GTX 1080 vs GTX 1080 Ti, don't confuse them
The 1080 Ti is a significantly faster card, 3,584 CUDA cores and 11 GB of GDDR5X against the plain 1080's 2,560 cores and 8 GB. They get lumped together in used listings constantly, confirm the exact model before buying.
RTX 2060 vs GTX 1080: your questions answered
It's close enough to call a coin flip on raw speed: the RTX 2060 averages roughly 6% higher frame rates, and that's the whole performance story between them. Ray tracing, DLSS, VRAM, and price end up mattering more than that small gap.
Get the RTX 2060 for DLSS and some ray tracing support at essentially the same speed for less money. Get the GTX 1080 if the extra 2 GB of VRAM and its wider 256-bit bus matter more to you than having those newer features.
Yes, for 1080p at medium to high settings both still hold up fine. Push into 1440p or Ultra presets in newer AAA titles and both start to strain, and the 6% gap between them won't change that outcome either way.
Not really. A 6% average speed bump doesn't offset giving up 2 GB of VRAM, so it lands closer to a sidegrade than an upgrade. Hold onto the 1080, or skip the 2060 entirely and save toward a used RTX 3060 instead.
The RTX 2060, because its 240 Tensor cores accelerate that kind of workload directly. The GTX 1080 has no Tensor cores at all, so its extra 2 GB of VRAM doesn't make up for lacking that dedicated hardware.
The RTX 2060 streams and encodes cleaner. Turing's NVENC block added HEVC B-frame support that Pascal's encoder in the GTX 1080 never got, and that shows up as a visible quality bump at matching bitrates.
No. Ray tracing and DLSS both need Tensor and RT cores, hardware the GTX 1080 doesn't have since it predates Turing entirely. The RTX 2060 carries 30 RT cores and 240 Tensor cores, so it's the only one of the two capable of either.
Neither one. DLSS 3 Frame Generation needs the Optical Flow Accelerator that only arrived with RTX 40-series cards. AMD's FSR 3 Frame Generation isn't locked to specific hardware, so that's the one frame-gen option open to both.
Unlikely at this performance tier. Both cards sit in a bracket a mid-range CPU keeps fed easily, run the pairing checker on this page, but a Ryzen 5 3600 or Core i5-10400F or newer is enough to avoid becoming the limiting factor at 1080p.
The GTX 1080 runs warmer and louder across the board. Its reference blower design pushes hotspot temps to around 85°C under load versus roughly 80°C on the RTX 2060, and it draws about 20 W more doing it.
500 W covers the RTX 2060 with room to spare. The GTX 1080 wants 550 W as the safe recommendation given its higher draw. A 600 W unit handles either one comfortably if you're planning ahead.
Check clearance for the GTX 1080 specifically, its reference card measures 267 mm, noticeably longer than the RTX 2060's compact 229 mm. Both use a standard PCIe 3.0 ×16 slot, so the interface itself is never the limiting factor.
Both exist as mobile parts, but treat them as separate products entirely. Laptop versions of the RTX 2060 and GTX 1080 run at lower clocks and tighter power limits than the desktop cards covered on this page.
No, not for current AAA games. Both cards are built for 1080p with occasional 1440p in lighter titles, and a 6% gap between them isn't nearly enough to make either one a real 4K option.
Used is the only sensible route for either card at this point. A used RTX 2060 around $75 gets you similar performance to a used GTX 1080 at roughly $90, plus DLSS and ray tracing capability the 1080 can't match.
Both still receive NVIDIA's Game Ready driver updates. Being three years newer, the RTX 2060's Turing architecture is the safer bet to keep that support going longer than the GTX 1080's Pascal, though neither is getting new architecture-level features from here.
