Nvidia’s RTX 5090 is a GPU with unique capabilities: the company’s highest-end consumer GPU to date features a whopping 21,760 CUDA cores and 32GB of GDDR7 memory in its reduced GB202 configuration.
It also happens to be one of the most expensive GPUs retail consumers can buy in 2026, priced up to twice its stated MSRP of $2,000 for the Founders Edition at launch, causing many cost-sensitive AI creators to turn to older Nvidia GPUs equipped with 24GB of VRAM, such as the RTX 4090, 3090Ti, and 3090.
As AI models continue to advance in complexity (and memory requirements), a DRAM crisis makes it impossible for many to secure a capable GPU for their local AI needs, even as one option seems largely ignored: Intel’s Arc Pro B70.
A mid-range GPU with tons of VRAM
Most consumers do not consider Intel a GPU manufacturer, but instead associate it with enterprise- and consumer-grade CPUs. This is despite the fact that the chipmaker offers some of the best value for money options in the mid-range segment in which it currently competes.
Intel’s Arc Pro offerings, however, are starkly different; They focus exclusively on professional-level, or rather, AI-centric workloads, and eschew any pretense of catering to gaming consumers, even while still being capable of running most titles that can be offered to them.
The Intel Arc Pro B70 is its highest-end offering and has a price tag of $950, with most retailers and OEM partners selling SKUs for around $1,000. With 32GB of GDDR6 memory and a price that’s effectively a quarter of most RTX 5090 SKUs on sale at the time of writing, it remains a value-focused alternative to Nvidia’s Blackwell-based behemoth.
It takes advantage of Intel’s BMG-G31 “Big Battlemage” chip that was originally scheduled to show up in its now-canceled Arc B770 GPU, as it aims to address a gap in the on-premises AI space that both AMD and Nvidia are unwilling to address given their focus on maximizing profits at the higher end of the spectrum with enterprise consumers.
For those interested in setting up the 4 Arc Pro B70, Puget Systems went ahead and performed the necessary testing, even doing a direct comparison with the RTX 5090, which it finds 4 to 5 times faster in decoding tasks thanks to a significantly greater amount of memory bandwidth at play (1792 GB/s vs. 608 GB/s).
However, the observations also pointed out a slightly obvious caveat in the comparisons: models that require more compute and bandwidth versus memory will lean towards the RTX 5090, which offers a significant advantage even against multiple Arc Pro B70 GPUs, but those that require a lot of memory for their parameters would find a B70 configuration a much more cost-effective option with access to more memory than a corresponding RTX 5090-based offering.
Nvidia’s value proposition, however, runs deeper than the silicon itself, and is where Intel struggles to find a willing buyer, thanks to better software support across multiple operating systems, CUDA-based software stacks that Arc Pro can’t emulate, and Nvidia-coded libraries that won’t work on Intel hardware.
Intel’s own offerings (oneAPI, OpenVINO, and IPEX) are improving, but are considered to be lagging behind even AMD’s ROCm stack, which in turn lags behind Nvidia’s ecosystem. Despite this, the Arc Pro B70, as noted above, benefits from the lack of a real high-VRAM alternative and remains available close to its stated MSRP, making it a formidable and scalable alternative to Nvidia’s heavy GPU.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds.
