There are a number of compact fashionable workstations that pack somewhat succesful CPUs, however on the identical time they lack the gap to house a typical high-performance workstation-grade graphics card. That normally limits them to entry-level GPUs with mediocre functionality. For those who desire a compact SFF workstation with extra graphics oomph, Nvidia has presented a brand new ProViz-oriented RTX 4000 SFF Ada Era (opens in new tab) graphics card. It is one of the most extra fascinating choices within the fresh years, packing a high-end GPU right into a low-profile form-factor, with an influence intake of simply 70W.

The Nvidia RTX 4000 SFF Ada board makes use of the corporate’s AD104 graphics processing unit with 6144 CUDA cores enabled (out of 7680 in overall). That is the identical GPU because the RTX 4070 Ti however with fewer energetic cores, and the spice up frequency will get capped at round 1560 MHz to decrease overall board energy. However, the graphics card comes with 20GB of GDDR6 reminiscence with ECC that connects to the GPU the usage of a 160-bit interface, so numerous reminiscence for workstation use.

The GPU comes with two NVENC encoders and two NVDEC decoders activated, although Nvidia has no longer touched upon precise features of those devices. They will have to be very similar to the NVENC and NVDEC utilized in different Ada playing cards, and you’ll see the video encoding functionality and high quality in our fresh roundup of GPUs.

The GA104 chip on this configuration delivers top unmarried precision functionality of nineteen.2 TFLOPS, making it theoretically similar to a GeForce RTX 3070. It has top RT functionality of 44.3 TFLOPS, and top FP8/INT8 tensor functionality of 306.8 TFLOPS/TOPS.


(Symbol credit score: Nvidia)

Nearly 20 FP32 TFLOPS could also be dwarfed by way of the overpowering functionality of Nvidia’s RTX 6000 Ada Era or GeForce RTX 4090, however the RTX 4000 SFF is a low-profile dual-slot graphics card that may are compatible into virtually any desktop laptop, even one that doesn’t have a spare auxiliary PCIe energy connector. Apparently, RTX 4000 Ada’s 153/306.8 INT8 TFLOPS (with out and with sparsity, respectively) functionality may be very with regards to that of Nvidia’s GeForce RTX 3090 Ti this is each dearer and way more energy hungry.

Swipe to scroll horizontally
Nvidia RTX 40-Sequence Specs
Row 0 – Cellular 0 GPU FP32 CUDA Cores FP32 TFLOPS INT8 TFLOPS Reminiscence Configuration TBP MSRP
GeForce RTX 4070 Ti AD104 7680 40 TFLOPS 160/320 TFLOPS 12GB 192-bit 21 GT/s GDDR6X 285W $799
GeForce RTX 4070 AD104 5888 (?) ? ? 12GB 192-bit 21 GT/s GDDR6X 250W (?) ?
RTX 4000 Ada Era AD104 6144 19.2 TFLOPS 153/307 TFLOPS 20GB 160-bit 16 GT/s GDDR6 ECC 70W $1,250
GeForce RTX 3090 Ti GA102 10,752 40 TFLOPS 160/320 TFLOPS 24GB 384-bit 20 GT/s GDDR6X 450W $1,999
GeForce RTX 3070 GA104 5888 20.31 TFLOPS 81/160 TFLOPS 8GB 256-bit 14 GT/s GDDR6 220W $499

Supply Via