BEST SELLERS

In Workstation Components

(1) It works. (2) It is faster than my TR 1950X. (3) It is faster than my R9 7950X at multi-threaded tasks. (4) It can run WinUAE in real-time without the need for JIT.

I got this PSU because it was rated best PSU by hardware busters in its class. It looks better and cleaner than the photographs. The photos almost dissuaded me from getting it because the back side looked rough, but the unit looks and feels high quality.

The performance is excellent. The card comes with FOUR mini-DisplayPort to regular DisplayPort adapters, which is appreciated. Included is a low-profile bracket that can be swapped, as needed.

Seller was knowledgable and nice. Card delivered in under a week and well packaged. They also confirmed it'd work in my Minisforum A2 ahead of time. This 4070 mobile card worked out of the box on Linux. The performance is in between an AMD 8060s and RTX 5070 mobile. Perf in a custom mod induced rough area in Baldur's Gate 3 (no upscaling and TAA iirc): 8060s - 52fps 4070 card (mobile) - 55fps 5070 mobile - 60fps All 3 systems have Zen5 CPUs. The Radeon image quality looks the best for some reason even on same monitor and cables, not sure why. Normally, all 3 of my systems are between 80-100fps in BG3 at 1080p on Linux kernel 7.2. I haven't hit Act3 yet so I tried to used a mod to simulate that experience. Witcher 3 next gen was running about 100fps at 1080p with everything turned up except RT. I turned my 8060s and 5070 mobile into local LLM systems and the 4070 mobile became my day to day gaming rig for Witcher 3, BG3 and CS2.

Ability to control the fan with a switch. Solid build Good cables

great for a workstation application

The PNY RTX PRO 5000 is worth every penny. It is lightning fast and handles enormous datasets with ease. It was delivered on time and expertly wrapped to avoid damage en route.

The low price and decent specs make this a solid card for getting into ML and transformer models, but the fact that it is two GPUs with 12gb of vram each limits things a bit from a coding perspective. Great for running things in batch, but very difficult to bridge with good performance.

Keep in mind this card has its limitations, I am looking at it from the stand point of this verse a RTX3090 used (about the same price). No way I am spending $1000 on a used card that can die tmw even with Cuda support. So now I get 32GB vs 24GB ram. I am primary running windows and LMstudio and Ollma worked fine after installing all the intel software (like 4 large installs) Vulkan support gave me around 100T/KS for qwen 3.5-35b. Out of the box with standard setup. This running on an Intel i7-11th gen with 64GB DDR4 and PCI 4 x8 interface.. The biggest hit is on how fast I can load the model in memory. The card is very quite with the fan. I suppose other people got loud fans.

Crazy power and upgradability.