AMD plans 16-core Ryzen 9000X3D CPU with 192 MB cache and 200 W TDP

AMD is reportedly preparing a 16-core Ryzen 9000X3D CPU with dual 3D V-Cache chiplets, an industry first, potentially setting a new gaming performance benchmark.

AMD is reportedly preparing to expand its forthcoming Ryzen 9000 ´Granite Ridge´ lineup with two new Zen 5 desktop CPUs, according to leaks from a well-connected source. One of the processors allegedly sports 8 cores and 16 threads, with a thermal design power of 120 W and a massive 96 MB of L3 cache—mirroring the cache density of the Ryzen 7 9800X3D, though it may be released as a separate SKU for enthusiasts seeking high-performance gaming and multitasking capabilities.

More significant, however, is the revelation of a 16-core, 32-thread flagship sporting a daunting 200 W TDP and an unprecedented 192 MB of L3 cache. This model, according to the leak, features a dual-chiplet (dual-CCD) architecture where both dies possess full 3D V-Cache stacking. Each chiplet purportedly pairs 32 MB of on-die cache with 64 MB of vertically stacked 3D V-Cache, resulting in the first AMD desktop CPU to offer 3D V-Cache on both dies. This is a notable departure from prior top-end designs, which have combined a single 3D V-Cache chiplet with a standard core complex die, limiting bandwidth and performance symmetry.

If confirmed, the introduction of dual-X3D stacking represents a major technological and economic breakthrough for AMD. The new design promises enhanced cache bandwidth across all threads and cores, eliminating previous compromises that bottlenecked multithreaded and gaming performance. For the desktop market, these chips could further cement AMD´s gaming dominance and, crucially, make high-capacity, dual-X3D dies available to mainstream users—a move that could influence competitive dynamics within the high-end processor segment as well as drive advancements in workload-optimized design. The industry is closely watching to see if AMD can turn this leak into a market reality and shift the standard for gaming and productivity CPUs in the process.

66

Impact Score

Google taps Intel for in-house Artificial Intelligence chips

Google’s potential order for in-house Artificial Intelligence accelerators would strengthen Intel’s contract manufacturing push as chip designers look beyond TSMC. Nvidia is also evaluating Intel technology for a multi-chip processor.

European Commission clarifies high-risk Artificial Intelligence rules

The European Commission’s draft guidance maps how high-risk Artificial Intelligence classifications may apply to agentic systems, regulated products, biometrics, employment tools, and financial services. The guidance signals narrow exceptions and a broad view of systems that materially influence regulated decisions.

NVIDIA confidential computing expands Apple private cloud compute

NVIDIA GPUs with Confidential Computing will support confidential inference for Apple’s Private Cloud Compute as it expands to Google Cloud. The collaboration brings NVIDIA Blackwell GPUs into the hardware security architecture behind some next-generation Apple Intelligence features.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.