Skip to main content
  1. Home
  2. Computing
  3. News

AMD’s latest Ryzen 9 9950X3D2 pushes X3D to the limit

Dual 3D V-Cache, higher power, and a focus on enthusiast performance

Add as a preferred source on Google
AMD Ryzen 9 9950X3D2 FEatured
AMD

AMD has unveiled what might be its most extreme desktop CPU yet, the Ryzen 9 9950X3D2. And it’s going all-in on one thing: cache.

💥 We pushed the limits of desktop performance with X3D. Then we pushed them further.

I’ve been testing the new unreleased Ryzen 9 9950X3D2 Dual Edition in the lab firsthand and it is incredible.

The world’s first desktop CPU with dual @AMD 3D V-Cache delivers 208MB of total… pic.twitter.com/Cm5mfSkeQm

— Jack Huynh (@jackhuynh) March 26, 2026

Building on the existing AMD Ryzen 9 9950X3D, the new chip introduces a dual 3D V-Cache design, meaning both core chiplets (CCDs) now get stacked cache instead of just one. The result? A massive 208MB of total cache, which is one of the highest ever seen on a consumer CPU.

What makes the 9950X3D2 different?

At its core (literally), this is still a 16-core, 32-thread Zen 5 processor, similar to the standard 9950X3D. But the big change is how AMD is handling cache this time. Traditionally, X3D chips only placed the extra 3D V-Cache on one CCD, balancing performance and clock speeds.

The 9950X3D2 flips that approach by putting stacked cache on both CCDs, effectively doubling the available L3 cache to around 192MB, taking the total cache up to 208MB. There’s a trade-off, though, as this comes with a higher 200W TDP, making it one of AMD’s more power-hungry desktop chips.

Why does all this cache matter?

Cache is essentially a shortcut for performance, especially in gaming. By increasing L3 cache, the CPU can access frequently used data faster, reducing memory latency and improving performance in CPU-heavy scenarios like esports titles and large open-world games. With the Ryzen 9 9950X3D2 doubling down on cache across both chiplets, AMD is clearly aiming to squeeze out even more gains, though there’s a point where adding more cache delivers diminishing returns depending on the workload.

That said, this chip isn’t meant for everyone. It’s designed for enthusiasts, high-end gamers, and power users who want top-tier performance regardless of power draw or cost. With its higher TDP and niche positioning, the 9950X3D2 feels more like a halo product, something that showcases what’s possible rather than something most users actually need.

From a bigger-picture standpoint, this CPU feels like AMD pushing X3D tech to its limits on Zen 5. It’s less about replacing existing chips and more about seeing how far cache-driven performance can go before Zen 6 arrives. AMD hasn’t revealed pricing yet, but the chip is set to launch on April 22nd. If nothing else, it reinforces that AMD is still betting big on cache as its gaming advantage.

Varun Mirchandani
Varun is an experienced technology journalist and editor with over eight years in consumer tech media. His work spans…
The Mac Pro nearly received an M3 Extreme chip twice as powerful as M3 Ultra
High production costs likely killed Apple’s M3 Extreme plans
Apple's Mac Pro on a table at a press event.

Apple discontinued the Mac Pro earlier this year, ending a 20-year run for a computer that once represented the very best of the company’s desktop lineup. However, Apple reportedly had much bigger plans for the machine before ultimately replacing it with the Mac Studio.

According to Bloomberg’s Mark Gurman, Apple developed an M3 Extreme chip that could have offered twice as many CPU and GPU cores as the M3 Ultra. The processor was intended to sit above the Ultra tier and could have finally given the Mac Pro the performance advantage it badly needed. Apple eventually abandoned the chip due to concerns over production costs and limited demand for such an expensive machine.

Read more
Hidden prompts can secretly rewrite an AI’s memory, and researchers say that’s a serious problem
Researchers discover AI attack that rewrites an assistant's long-term memory
Chatbot on a smartphone.

Large language models are getting better at remembering us. Whether it's your preferred writing style, recurring tasks, shopping habits or project deadlines, AI assistants are increasingly storing long-term memories to make future conversations feel more personal and useful. But according to new research, that same feature could become one of AI's biggest security vulnerabilities.

Researchers from New Mexico State University have demonstrated a new attack called GhostWriter, capable of secretly planting false memories inside AI agents. Rather than stealing information outright, the attack manipulates what an AI remembers, potentially causing it to make dangerous decisions long after the original attack has taken place.

Read more
This experiment shows how easy it is to poison an open-weight AI model for under $100
This research raises new doubts about trusting open weight AI models.
Computer, Electronics, Laptop

Open-weight AI models have been having a moment lately. Just this month, Moonshot's massive Kimi K3 model landed close behind Claude Fable 5 and GPT 5.6 Sol in several benchmarks, all while remaining fully open-weight and downloadable by anyone.

However, Katie Paxton-Fear, a cybersecurity lecturer at Manchester Metropolitan University and staff security advocate at Semgrep, managed to poison an open-weight model and proved how easily that openness can be turned against you (via The Register).

Read more