NVIDIA GeForce RTX 5080 GPU Custom Model Leak: 16 GB GDDR7 Memory and 2.2 Slot Design Revealed

Recent leaks have unveiled NVIDIA’s GeForce RTX 5080 custom model, offering an intriguing glimpse into the designs of next-generation gaming GPUs.

First Look at NVIDIA GeForce RTX 5080 Custom Model: Enhanced Cooling and Design Features

The NVIDIA GeForce RTX 5080 will be one of the initial offerings in the RTX 50 series, codenamed “Blackwell.”Among the leaked models, MSI’s GeForce RTX 5080 Gaming Trio OC Edition stands out with an updated aesthetic and functionality.

This new model adopts a more compact 2.2-slot design, replacing the bulkier 3.5-slot configuration found in the RTX 4080 Gaming Trio. The leak showcases a design evolution while maintaining the card’s signature look.

NVIDIA GeForce RTX 5080 Custom Model — Image Source: Chiphell Forums

Equipped with a tri-fan cooling system, this iteration utilizes the Tri Frozr 4 technology, an enhancement over the previous Tri Frozr 3 found in earlier RTX 40 series models. The specifications reveal impressive features, including:

Dedicated Ray Tracing Cores
Dedicated Tensor Cores
NVIDIA DLSS Support
Game Ready and NVIDIA Studio Drivers
NVIDIA APP Integration
NVIDIA Broadcast Capabilities
NVIDIA G-Sync Compatibility

NVIDIA GeForce RTX 5080: Key Specifications

Featuring the PG144/147-SKU45 PCB architecture and the robust GB203-400-A1 GPU die, the RTX 5080 leverages a complete implementation of the GB203 GPU with 84 Streaming Multiprocessors (SMs) and a total of 10,752 cores. This represents a notable decrease of approximately 51% in core count compared to the anticipated RTX 5090, suggesting significant performance variability compared to its predecessor.

Unlike prior models, the RTX 5080 offers a reduced VRAM setup with 16 GB, operating on a 256-bit bus and harnessing the high-speed GDDR7 memory. With maximum speeds reaching 32 Gbps, this configuration provides a total bandwidth of 1024 GB/s (or 1 TB/s). The graphics card is designed with a total board power (TBP) of 400W, marking a 25% increase and indicating potential real-world performance improvements.

Preliminary Specifications for NVIDIA GeForce RTX 50 Series GPUs

Graphics Card Name	NVIDIA GeForce RTX 5090	NVIDIA GeForce RTX 5080	NVIDIA GeForce RTX 5070 Ti	NVIDIA GeForce RTX 5070	NVIDIA GeForce RTX 5060 Ti	NVIDIA GeForce RTX 5060
GPU Name	Blackwell GB202-300	Blackwell GB203-400	Blackwell GB203-300-A1	Blackwell GB205-300-A1	Blackwell GB206?	Blackwell GB206?
GPU SMs	170 (192 Full)	84 (84 Full)	70 (84 Full)	50 (50 SM Full)	TBD	TBD
GPU Cores	21,760 (+33%)	10,752 (+11%)	8,960 (+16%)	6,144	TBD	TBD
Clock Speeds	TBD	TBD	TBD	TBD	TBD	TBD
L2 Cache	TBD	TBD	TBD	TBD	TBD	TBD
Memory Capacity	32 GB GDDR7 (+33%)	16 GB GDDR7 (0%)	16 GB GDDR7	12 GB GDDR7	16 GB GDDR7	8 GB GDDR7
Memory Bus	512-bit (+33%)	256-bit (0%)	256-bit (0%)	192-bit (0%)	128-bit (0%)	128-bit (0%)
Memory Speed	28 Gbps	30 Gbps	28 Gbps	28 Gbps	28 Gbps?	28 Gbps?
Bandwidth	1792 GB/s	1024 GB/s	896 GB/s	672 GB/s	448 GB/s	448 GB/s
TBP	600W (+33%)	400W (+25%)	300W (+10.5%)	250W (+14%)	TBD	TBD
Power Interface	1 12V-2×6 (16-Pin)	1 12V-2×6 (16-Pin)	1 12V-2×6 (16-Pin)	1 12VHPWR (16-Pin)	1 12VHPWR (16-Pin)	1 12VHPWR (16-Pin)
Launch Window	Q1 2025	Q1 2025	Q1 2025	Q1 2025	TBD	TBD