Benchmarks for the “Cancelled” RTX 4080 12GB Leaked, Shows Disappointing Performance

Chiphell Forums now has benchmarks for the recently discontinued NVIDIA GeForce RTX 4080 12GB graphics card, giving us a glimpse of the AD104 GPU’s potential capabilities.

The NVIDIA GeForce RTX 4080 12 GB graphics card was scheduled to be on sale starting next month for $899 US. However, considering the stark performance difference between the 16 GB and 12 GB variants, NVIDIA chose to scrap the 12 GB model while continuing to plan to deliver the 16 GB model on November 16. Given how quickly the launch was postponed, AIBs undoubtedly received a batch of Ada AD104 GPUs to create their own models,  and these cards were unquestionably prepared to be sent to distributors and stores. Now, despite the cancellation, standards for gaming and synthetic technology are beginning to surface.

This particular GeForce RTX 4080 12 GB graphics card lacks information such as the model number, but it does have a maximum GPU rate of 2820 MHz and uses 262W of electricity. In the AIDA64 GPGPU test, the GPU was able to provide a peak FP32 computation power of 42 TFLOPs. Other simulated benchmarks performed on the NVIDIA GeForce RTX 4080 12 GB graphics card resulted in scores of 5382 in 3DMark Speed Way, 10794 in 3DMark Time Spy Extreme, 13472 in 3DMark Fire Strike Ultra, and 66.98 FPS in the DXR Feature Test.

The in-game benchmark for Cyberpunk 2077 was also tested at 4K with Ray Tracing enabled. The GPU averaged 67.52 frames per second.

The now-cancelled RTX 4080 12GB was equipped with the AD104-400 GPU along with 7680 CUDA cores. It was speculated to come with 12 GB of GDDR6X capacity since the GPU would have had a 192-bit bus interface and 48 MB of L2 cache. According to reports, the memory operated at 21Gbps speeds, providing 504 GB/s of memory bandwidth. The card’s alleged boost clock was 2610 MHz, although the peak frequency would have been greater.

The RTX 4080 12 GB has been referred to by enthusiasts as a “imposter GPU.” In reality, this GPU is advertised as an 80 series chip while having 70 class requirements. This choice was met with harsh criticism, which may have put NVIDIA in a difficult situation leading to its cancellation.

NVIDIA RTX 4000 Series Formal Specifications:

SKUChipFP32/CUDASMsMax ClockCacheMemory BusVRAMMemory SpecSpeed (Gbps)TDP
RTX 4000 TitanAD102-450184321443.0GHz+?96MB?384/382-bit48GBGDDR6X24~800W
RTX 4090 TiAD102-350181761423.0 GHz?96MB382-bit24GBGDDR6X24600W?
RTX 4090AD102-300-A1163841282.52GHz96MB384-bit24GBGDDR6X21
450W+ (TGP) / 660W (Max TGP)
RTX 4080 TiAD102148481162.7 GHz?80MB?320-bit20GBGDDR6X23420W
RTX 4080 (16GB)AD103-300-A19728762.505GHz64MB256-bit16GBGDDR6X22.5
320W(TGP)/ 516W (Max TGP)
RTX 4070 Ti (4080 12GB Revamped)AD104-400-A17680602.61GHz48MB192-bit12GBGDDR6X21285W (TGP) /366W (Max TGP)
RTX 4070 AD104-300?716856>2.5GHz?48MB?160-bit?/192-bit12GB?GDDR6X21?
300W
Muhammad Zuhair
Passionate about technology and gaming content, Zuhair focuses on analysing information and then presenting it to the audience.
Back to top button