PopularAcer’s new RTX Spark is a compact AI workstation pairing NVIDIA Blackwell graphics with a Grace CPU and up to 128GB of unified memory.
TL;DR: Acer’s SFF RTX Spark is a compact AI workstation concept using NVIDIA’s RTX Spark platform: a Blackwell GPU with Grace CPU, up to 6,144 CUDA cores, 1 petaflop FP4 AI compute and 128GB unified memory for shared CPU-GPU workloads; pricing and availability remain unconfirmed.
Acer has unveiled its first compact PC based on NVIDIA’s RTX Spark platform, aiming to challenge systems like the Mac Studio with 128GB of unified memory and a full petaflop of AI compute.
VIEW GALLERY – 2 IMAGES
The Acer SFF RTX Spark features an NVIDIA Blackwell GPU and a Grace CPU, delivering up to 6,144 CUDA cores and 1 petaflop of FP4 AI compute. The new system is designed for local AI workloads, content creation, and gaming, with Acer saying it supports NVIDIA’s CUDA and RTX technologies.
Acer showed the system at IFA 2026, though it is calling it a design concept rather than a finalized product, which is a nice way of saying Acer is currently in the process of gauging the public reaction to the released specifications and design before it initiates any production on the new system.
The 128GB unified memory architecture is a major draw, enabling seamless data sharing between the CPU and GPU, which makes the platform particularly attractive to developers and creators looking to run local AI models and reduce reliance on AI cloud infrastructure. NVIDIA is promoting the RTX Spark platform for both compact desktops and thin laptops, hinting at broader adoption.
Frequently Asked Questions
Open a question for an answer from TweakTown’s coverage of this news, or ask your own below.
Question #1
What kinds of local AI workloads is the RTX Spark designed to run with its 128GB unified memory?
It is designed to run local AI workloads, especially local AI models that benefit from shared CPU and GPU memory. Acer also frames it as a system for content creation, with the 128GB unified memory meant to make local AI processing easier and reduce reliance on cloud infrastructure.
Question #2
How does the RTX Spark’s Grace CPU and Blackwell GPU work together in Acer’s compact design?
Acer’s compact RTX Spark pairs the Grace CPU with the Blackwell GPU through a 128GB unified memory architecture, so both components can share data seamlessly. That setup is aimed at local AI workloads, content creation, and gaming, with the GPU providing up to 6,144 CUDA cores and 1 petaflop of FP4 AI compute.
Question #3
Will Acer offer different memory or storage configurations for the RTX Spark beyond 128GB unified memory?
No. Acer has only shown the RTX Spark concept with up to 128GB of unified memory and has not confirmed any other memory or storage configurations. It also has not confirmed pricing, dimensions, or availability.
Question #4
Is the RTX Spark intended for developers only, or will it also target general desktop users?
It is not positioned as developers only. Acer says the system is designed for local AI workloads, content creation, and gaming, and NVIDIA is promoting RTX Spark for both compact desktops and thin laptops, which points to broader use. At the same time, the memory and AI focus make it especially attractive to developers and creators.
Have a question about this content not listed here? Ask below and TweakBot will answer it.
TweakBot is analyzing your question…
TweakBot is generating an answer
Was TweakBot helpful?Thanks for the feedback!
Acer has yet to confirm pricing, dimensions, or availability. But with 128GB unified memory and Blackwell under the hood, the SFF RTX Spark is shaping up as a serious contender in the high-end compact PC space. However, expect an eye-watering price tag, given widespread hardware price increases and the system rocking NVIDIA’s bleeding-edge, AI-focused technology.