NVIDIA has launched its brand new Ada GPU for professionals, the RTX 2000 Ada, which aims at the entry-level price segment.
NVIDIA's RTX 2000 Ada GPU Now Official: $625 US With 16 GB VRAM & 2816 Cores
The NVIDIA RTX 2000 Ada GPU targets the entry-level prosumer segment and aims to be one of the leading products for the masses who want a compact graphics solution for AI-accelerated design & visualization. The main highlights of the new graphics card include:
- Third-generation RT Cores: Up to 1.7x faster ray-tracing performance for high-fidelity, photorealistic rendering.
- Fourth-generation Tensor Cores: Up to 1.8x AI throughput over the previous generation, with structured sparsity and FP8 precision to enable higher inference performance for AI-accelerated tools and applications.
- CUDA cores: Up to 1.5x the FP32 throughput of the previous generation for significant performance improvements in graphics and compute workloads.
- Power efficiency: Up to a 2x performance boost across professional graphics, rendering, AI and compute workloads, all within the same 70W of power as the previous generation.
- Immersive workflows: Up to 3x performance for virtual-reality workflows over the previous generation.
- 16GB of GPU memory: An expanded canvas enables users to tackle larger projects, along with support for error correction code memory to deliver greater computing accuracy and reliability for mission-critical applications.
- DLSS 3: Delivers a breakthrough in AI-powered graphics, significantly boosting performance by generating additional high-quality frames.
- AV1 encoder: Eighth-generation NVIDIA Encoder, aka NVENC, with AV1 support, is 40% more efficient than H.264, enabling new possibilities for broadcasters, streamers, and video callers.
In terms of specifications, the NVIDIA RTX 2000 Ada is based on the AD107 GPU with 2816 CUDA cores, 88 Tensor Cores, 22 RT cores and offers 12 TFLOPs of FP32, 27.7 TFLOPs of RT Core and up to 191.9 TFLOPs of tensor-core performance. The graphics card also comes with a 16 GB GDDR6 memory interface running at 16 Gbps across a 128-bit wide bus interface. The graphics card has a total board power or TBP of 70W.
In terms of design, the NVIDIA RTX 2000 Ada GPU comes in a dual-slot and HFHL design with four MiniDisplayPort 1.4a outputs and the same AV1 encoding and decoding capabilities found on the Ada Lovelace architecture. The graphics card is already supported in the latest RTX Enterprise GPU drivers which now offer new support for features such as Video Super Resolution, TrueHDR, and more. The driver also enables TensorRT-LLM support, offering a rich AI experience in a range of LLMs.
As for availability, the reference design will be available at a starting price of $625 US from partners such as Arrow Electronics, Ingram Micro, Leadtek, PNY, Ryoyo Electro, and TD SYNNEX, and will be available from Dell Technologies, HP, and Lenovo starting in April.
NVIDIA RTX Ada Workstation Graphics Card Lineup:
| Graphics Card | RTX 6000 Ada | RTX 5880 Ada | RTX 5000 Ada | RTX 4500 Ada | RTX 4000 Ada | RTX 4000 SFF Ada | RTX 2000 SFF Ada | RTX 2000E SFF Ada |
|---|---|---|---|---|---|---|---|---|
| GPU | Ada Lovelace GPU | Ada Lovelace GPU | Ada Lovelace GPU | Ada Lovelace GPU | Ada Lovelace GPU | Ada Lovelace GPU | Ada Lovelace GPU | Ada Lovelace GPU |
| GPU Process | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N |
| Die Size | 608mm2 (AD102) | 608mm2 (AD102) | 608mm2 (AD102) | 295mm2 (AD104) | 295mm2 (AD104) | 295mm2 (AD104) | 159mm2 (AD107) | 159mm2 (AD107) |
| GPU Cores | 18176 Cores | 14,080 | 12800 Cores | 7680 Cores | 6144 Cores | 6144 Cores | 2816 | 2816 |
| Tensor Cores | 568 Cores | 440 Cores | 500 Cores | 300 Cores | 192 Cores | 192 Cores | 88 | 88 |
| Boost Clock | 2.50 GHz | ~2.50 GHz | ~2.60 GHz | ~2.60 GHz | ~2.20 GHz | ~1.70 GHz | TBD | TBD |
| Single Precision | 91.1 TFLOPs | 69.3 TFLOPs | 65.3 TFLOPs | 39.6 TFLOPs | 26.7 TFLOPs | 19.2 TFLOPs | 12 TFLOPs | 8.9 TFLOPs |
| Tensor Performance | 1458 TFLOPs | 1108 TFLOPs | 1044 TFLOPs | 634 TFLOPs | 327 TFLOPs | 306.8 TFLOPs | 191.9 TFLOPs | 143 TFLOPs |
| VRAM | 48 GB GDDR6 | 48 GB GDDR6 | 32 GB GDDR6 | 24 GB GDDR6 | 20 GB GDDR6 | 20 GB GDDR6 | 16 GB GDDR6 | 16 GB GDDR6 ECC |
| NVLINK VRAM | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A |
| Memory Bus | 384-bit | 384-bit | 256-bit | 192-bit | 160-bit | 160-bit | 128-bit | 128-bit |
| Memory Bandwidth | 960 GB/s | 960 GB/s | 576 GB/s | 432 GB/s | 360 GB/s | 320 GB/s | 224 GB/s | 224 GB/s |
| TDP | 300W | 285W | 250W | 210W | 130W | 70W | 70W | 50W |
| Launch Price | $6800 US | TBD | $4000 US | $2250 US | $1250 US | $1250 US | $625 US | $849 US |
| Launch Date | Q1 2023 | Q1 2024 | Q3 2023 | Q4 2023 | Q4 2023 | Q1 2023 | Q1 2024 | Q3 2024 |
About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.
Follow Wccftech on Google to get more of our news coverage in your feeds.
