← All hardware
The previous-gen Ada flagship that remains a 24GB powerhouse for gaming and AI.
Pros
- Still one of the fastest GPUs for 4K gaming and AI
- 24GB VRAM excellent for large AI models and rendering
- Proven, mature driver and ecosystem support
Cons
- Lacks DLSS 4 Multi Frame Generation
- End-of-life: production ended late 2024, new units scarce and heavily overpriced
- High 450W power draw
✓ Where it shines / best for
- 4K and high-refresh enthusiast gaming
- AI/ML researchers and creators needing 24GB VRAM
- Professional 3D rendering and video production
✕ Not the best fit for
- Budget or mid-range builds
- Small-form-factor cases (large, high-power card)
- Buyers wanting current-gen DLSS 4 multi-frame generation
Features
- ✓ Ada Lovelace architecture with 16,384 CUDA cores
- ✓ 24GB GDDR6X on a 384-bit bus, ~1,008 GB/s bandwidth
- ✓ DLSS 3 with Frame Generation
- ✓ 4th-gen Tensor cores and 3rd-gen RT cores
- ✓ 450W TGP, requires 16-pin (12VHPWR) power
- ✓ PCIe 4.0 interface
- ✓ AV1 dual encoders (NVENC)
Pricing
| Plan | Price | Billing | Notes |
|---|---|---|---|
| MSRP (Founders Edition) | $1,599 | one-time | Launch MSRP Oct 2022. Largely discontinued/end-of-life after RTX 5090 launch; street prices elevated. |
Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.
Specifications
| power | 450W TDP |
| memory | 24GB GDDR6X, 384-bit, 1,008 GB/s |
| interface | PCIe 4.0 |
| cuda_cores | 16,384 |
| architecture | Ada Lovelace (TSMC 4N) |
Sponsored
A full review is being generated for this product and will appear here shortly.