Tuesday, October 13th 2026

AMD Showcases Its Next-Gen EPYC "Verano" CPU, Up to 192 Cores and LPDDR5X Memory

AMD showed off its next-generation EPYC "Verano" server CPUs during CEO Dr. Lisa Su opening keynote at the 2026 OCP Global Summit. The new CPU is the first EPYC processor to support LPDDR5X memory via SOCAMM2 modules. Now AMD is mirroring rival NVIDIA's Vera CPU that already uses SOCAMM2 modules. The "Verano" processor sits within the EPYC 9006 "LP" family and is built on the same TSMC 2 nm process as the already-launched EPYC "Venice". While AMD "Venice" is the first EPYC processor based on Zen 6 architecture, "Verano" is optimized for AI tasks in agentic AI racks. For this, AMD plans to pair them with its own Instinct MI500 GPUs via xGMI connectivity at up to 112 Gbps. It will run on the new SP8 platform rather than Venice's SP7. When we first heard about "Verano", AMD indicated that the upcoming CPUs will feature up to 72 cores on a single-socket platform. However, that has now been updated to up to 192 cores.

From the initial information available, this could mean either a single large chip or a dual 96-core configuration. More details came from System360Cheese on X, who reported that the chip shown featured eight Zen 6 CCDs alongside two large IO dies and four LPDDR5X memory controllers. The CCDs appear smaller than those in Venice's Zen 6C design, suggesting these are the standard 12-core Zen 6 dies rather than the denser 32-core Zen 6C variants. The announcement follows AMD's earlier reveal of the Helion agentic AI rack, an Open Compute Project spec-designed system that Verano is expected to be integrated. Availability is targeted for 2027.
Sources: AMD, Wccftech, System360Cheese on X
Add your own comment

5 Comments on AMD Showcases Its Next-Gen EPYC "Verano" CPU, Up to 192 Cores and LPDDR5X Memory

#1
jesdals
Looking forward to Zen 6 and this could be a exciting preview
Posted on Reply
#2
XeonsNOpterons
I think clock speeds are going to be underwhelming for Zen 6 desktop given no bump to Venice over Turin in turbo clocks, but still really like that AMD went with much tighter packing of the chiplets. Very weird, Intel has been using this superior tight packing technique since Sapphire Rapids and now is moving away from it with Diamond Rapids and using effectively the die "island" approach AMD has been until Venice XD. Hopefully latency will not be a major bottleneck for Diamond Rapids.

192-cores is very impressive for the "small" socket.
Posted on Reply
#3
Wirko
XeonsNOpteronsI think clock speeds are going to be underwhelming for Zen 6 desktop given no bump to Venice over Turin in turbo clocks, but still really like that AMD went with much tighter packing of the chiplets. Very weird, Intel has been using this superior tight packing technique since Sapphire Rapids and now is moving away from it with Diamond Rapids and using effectively the die "island" approach AMD has been until Venice XD. Hopefully latency will not be a major bottleneck for Diamond Rapids.

192-cores is very impressive for the "small" socket.
It's surprising that Intel moved the chips apart ... I can only see heat density as the reason, it might become unmanageable if they were packed tight.
Posted on Reply
#4
XeonsNOpterons
WirkoIt's surprising that Intel moved the chips apart ... I can only see heat density as the reason, it might become unmanageable if they were packed tight.
Indeed, that may be the case, but it will likely be detrimental to performance. Though from what I know and expect, the hypothetically named 256-core Xeon 7980P will have a TDP around 650W, not much more than the EPYC 9996. And Intel's CBBs are massive, likely 600mm2, so I do not see the heat density being that much of a problem. Who knows, maybe Intel surprises us with a 1MW toaster chip lol.

Another prossibility is just leaving space on the substrate PCB to put more dies in the future. Coral Rapids-AP is supposed to reach 320-cores, and honestly, looking by the area open on the PCB with Diamond Rapids, Intel could slap another two CBBs in and have a 384-core chip if they wanted, but I assume their IO die is not designed to feed six dies.
Posted on Reply
#5
liveaxel
XeonsNOpteronsI think clock speeds are going to be underwhelming for Zen 6 desktop given no bump to Venice over Turin in turbo clocks, but still really like that AMD went with much tighter packing of the chiplets. Very weird, Intel has been using this superior tight packing technique since Sapphire Rapids and now is moving away from it with Diamond Rapids and using effectively the die "island" approach AMD has been until Venice XD. Hopefully latency will not be a major bottleneck for Diamond Rapids.

192-cores is very impressive for the "small" socket.
Considering AMD is going from N4 with Zen 5 to N2P on Zen 6 desktop, I'd expect there to be a very large clock speed boost. Rumors are that AMD was shooting for 7Ghz peak boost clocks, and that doesn't seem extreme considering both Apple and Qualcomm are hitting 5Ghz in their smartphone SoCs on N2P.
Posted on Reply
Nov 12th, 2026 04:40 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts