NVIDIA Unveils Next-Gen Feynman GPU In Updated Roadmap, Arriving in 2028 With Next-Gen HBM Memory

Hassan Mujtaba
Image Credits: Wccftech

NVIDIA has just named its next-generation GPU that arrives after Blackwell and Rubin, called Feynman, and it will use a new HBM memory.

NVIDIA Feynman Is The Name of Green Team's 2028's GPU, Will Use Next-Gen HBM Memory Too

At GTC 2025, NVIDIA unveiled its latest product roadmap which extends beyond the Rubin & Rubin Ultra GPUs. This new roadmap confirmed the company's next-gen GPU, which will be codenamed, Feynman, after renowned American theoretical physicist, Richard Phillips Feynman, who is known for his work on quantum mechanics.

Related Story NVIDIA Blackwell Sweeps Every MLPerf 6.0 Benchmark With No Competition In Sight, While GB300 Systems Run Up to 60% Faster Than GB200

Richard Phillips Feynman (/ˈfaɪnmən/; May 11, 1918 – February 15, 1988) was an American theoretical physicist. He is best known for his work in the path integral formulation of quantum mechanics, the theory of quantum electrodynamics, the physics of the superfluidity of supercooled liquid helium, and in particle physics, for which he proposed the parton model.

via Wikipedia

Although the company isn't announcing any in-depth details on the Feynman GPU yet, they did state that the GPU will be making use of next-gen HBM memory, so maybe HBM4e or HBM5?

In addition to that, NVIDIA's Feynman GPUs will also be equipped alongside the same Vera CPUs that will be utilized by the Rubin and Rubin Ultra platforms. More details on these are here too. Other upgrades will come in the form of the 8th Gen NVSwitch NVL-Next, Spectrum7 (204T, CPO) & CX10. These upgrades will be arriving sometime in 2028 and, given NVIDIA's timeline, we can expect a 2H launch. Also, there's no word on a Feynman Ultra for now, but we do expect to see an upgraded chip in the future, close to 2030.

NVIDIA Data Center / AI GPU Roadmap

GPU CodenameFeynmanRubin (Ultra)RubinBlackwell (Ultra)BlackwellHopperAmpereVoltaPascal
GPU FamilyGF200?GR300?GR200?GB300GB200/GB100GH200/GH100GA100GV100GP100
GPU SKUF200?R300?R200?B300B100/B200H100/H200A100V100P100
Process TechTSMC A16?TSMC N2P?TSMC N3P?TSMC 4NPTSMC 4NPTSMC 5nmTSMC 7nmTSMC 12nmTSMC 16nm
CPURosaVeraVeraGraceGraceGraceN/AN/AN/A
MemoryHBM4e/HBM5?HBM4HBM4HBM3eHBM3eHBM2e/HBM3/HBM3eHBM2eHBM2HBM2
Launch202820272026202520242022-20242020-202220182016
Hassan Mujtaba Photo

About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.

Follow Wccftech on Google to get more of our news coverage in your feeds.

Button