ZOTAC RTX 4090 Has Been Pictured, Features A Massive 4-Slot Design

Behold, the RTX 4090. This beast with the power it packs, requires an exotic cooling design which is fulfilled by the triple fan and a 4 slot design. Over at Baidu, Koko 218 posted a few images showcasing ZOTAC’s AMP EXTREME RTX 4090.
The Design
The front features a blackish texture accompanied by a silver-like covering at the edges whereas the backplate is covered in a black finish with a part of the chip exposed. The best (Kind of the worst) part is the logo confirmation. Instead of sticking with the bold logo, team green has opted for a plain design. It may not look the most aesthetic, however, it works.

The new logo design features 2 different fonts, namely GEFORCE RTX (Old) and the new NVIDIA Sans NALA. The latter supposedly reduces the thickness of the text as shown by Videocardz in a tweet.

Additional Features
ZOTAC’s signature technologies such as ICESTORM 3.0, SPECTRA 2.0, FREEZE & FIRESTORM are included with this variant. The ‘key features’ for the RTX 4090 appear blurred, possibly on purpose by the leaker. It means that NVIDIA may be introducing something new with Lovelace. We could only decipher a few features such as :
- PCIe 4.0
- CUTTING EDGE OPTIX
- AI-ACCELERATED PERFORMANCE
- REALISTIC AND IMMERSIVE GRAPHICS
- GAME —– RESPONSIVENESS
- BUILT FOR LIVE STREAMING
- AI-ENHANCED VOICE AND VIDEO
- FAST-TRACK YOUR CREATIVITY
- FINE-TUNED PERFORMANCE
The RTX 4090
A few days ago the RTX 4090 was tested in TSE and turned out to be 3x faster than the RTX 3080 from Ampere. The kingpin 4090 features the AD102 GPU along with 24GB of G6X memory. The initial launch lineup of Lovelace should only include the RTX 4090, the RTX 4080 and the RTX 4070. We expect to hear more from NVIDIA themself on the 20th of September at their GTC Keynote. Stay tuned for more information.
SKU | Chip | FP32/CUDA | Max Clock | Cache | Memory Bus | VRAM | Memory Spec | Speed (Gbps) | TDP | |||
RTX 4090 Ti | AD102-350 | 18432 | 3.0 GHz? | 96MB | 382-bit | 24GB | GDDR6X | 24 | 600W? | |||
RTX 4090 | AD102-300 | 16384 | 3.0GHz+ | 96MB | 382-bit | 24GB | GDDR6X | 23 | 450W | |||
RTX 4080 Ti | AD102 | 14848? | 2.7 GHz | 80MB? | 320-bit | 20GB | GDDR6X | 23 | 420W | |||
RTX 4080 | AD103-300 | 10240 | 3.2 GHz | 64MB | 256-bit | 16GB | GDDR6X | 23 | 320W | |||
RTX 4080 (Variant 1) | AD103-300-A1 | 9728 | 3.1GHz? | 48MB | 256-bit | 16GB | GDDR6X | 23 | 320W | |||
RTX 4080 (Variant 2) | AD103-300 | 9728 | 3.1GHz | 48MB? | 256-bit/192-bit | 12GB | GDDR6X | 23? | ||||
RTX 4070 Ti | AD104-400? | 7680 | 3.0GHz | ? | 192-bit | 12GB | GDDR6X | 21 | 300W? | |||
RTX 4070 (Original) | AD104-275? | 7680 | >2.7GHz | ? | 192-bit | 12GB | GDDR6X | 21 | 285W | |||
RTX 4060 Ti | AD104 | 6656 | 3.2 GHz? | 40MB? | 160-bit | 10GB | GDDR6X (?) | 18 | 275W | |||
RTX 4060 | AD106 | 4352 | 3.0 GHz? | 32MB | 128-bit | 8GB | GDDR6X (?) | 18 | 240W |