Intel officially releases Xeon 600 chips, announces new vPro Panther Lake CPUs — ‘all-new’ vPro platform goes all-in on AI
OEM and retail units are now available, plus new W890-chipset motherboards.
After revealing them last month, Intel has officially launched its Xeon 600 range of workstation CPUs. Previously known as Granite Rapids-WS, the range includes 11 SKUs, five of which will be available in boxed retail units. The chips support Intel’s updated vPro platform, alongside a range of Panther Lake chips that are now certified for business use with vPro.
Intel hasn’t shared new benchmarks for its Xeon 600 CPUs, still leaning on a claim of up to 61% faster multithreaded performance and up to 9% better single-threaded performance compared to last-gen Sapphire Rapids-WS chips. The news is that Xeon 600 CPUs are now available, starting at $499 and going up to $7,699. That includes OEM systems, boxed retail units, and motherboards with the new W890 chipset; though, Intel says you need to check with individual retailers on specific SKU availability.
As a recap, Xeon 600 are supported on the new W890 chipset, supporting up to 4TB of ECC memory in eight channels at up to 8000MT/s. The platform also supports up to 128 PCIe 5 lanes. For the chips themselves, they scale up to 86 scores using the Redwood Cove microarchitecture. Xeon 600 chips exclusively use the P-core design, with support for Hyper-Threading. They also come with Intel AMX in each core, with support for FP16 instructions to accelerate AI workloads, along with AVX-512 support.
| Row 0 - Cell 0 | 698X | 696X | 678X | 676X | 674X | 658X | 656 | 654 | 638 | 636 | 634 |
Cores / Threads | 86 / 172 | 64 / 128 | 48 /96 | 32 / 64 | 28 / 56 | 24 / 48 | 20 / 40 | 18 / 36 | 16 / 32 | 12 / 24 | 12 / 24 |
Frequency (Base / Boost) | 2 GHz / 4.8 GHz | 2.4 GHz / 4.8 GHz | 2.4 GHz / 4.9 GHz | 2.8 GHz / 4.9 GHz | 3 GHz / 4.9 GHz | 3 GHz / 4.9 GHz | 2.9 GHz / 4.8 GHz | 3.1 GHz / 4.8 GHz | 3.2 GHz / 4.8 GHz | 3.5 GHz / 4.7 GHz | 2.7 GHz / 4.6 GHz |
All-core Turbo | 3 GHz | 3.5 GHz | 3.8 GHz | 4.3 GHz | 4.3 GHz | 4.3 GHz | 4.5 GHz | 4.5 GHz | 4.5 GHz | 4.5 GHz | 3.9 GHz |
L3 Cache | 336MB | 336MB | 192MB | 144MB | 144MB | 144MB | 72MB | 72MB | 72MB | 48MB | 48MB |
Base TDP | 350W | 350W | 300W | 275W | 270W | 250W | 210W | 200W | 180W | 170W | 150W |
Memory channels | 8 | 8 | 8 | 8 | 8 | 8 | 8 | 8 | 4 | 4 | 4 |
MRDIMM Support | 8000 MT/s | 8000 MT/s | 8000 MT/s | 8000 MT/s | 8000 MT/s | — | — | — | — | — | — |
PCIe 5.0 Lanes | 128 | 128 | 128 | 128 | 128 | 128 | 128 | 128 | 80 | 80 | 80 |
Boxed | — | Yes | Yes | Yes | — | Yes | — | Yes | — | — | — |
Suggested Price | $7699 | $5599 | $3749 | $2499 | $2199 | $1699 | $1399 | $1199 | $899 | $639 | $499 |
As a recap, Xeon 600 are supported on the new W890 chipset, supporting up to 4TB of ECC memory in eight channels at up to 8000MT/s. The platform also supports up to 128 PCIe 5 lanes. For the chips themselves, they scale up to 86 scores using the Redwood Cove microarchitecture. Xeon 600 chips exclusively use the P-core design, with support for Hyper-Threading. They also come with Intel AMX in each core, with support for FP16 instructions to accelerate AI workloads, along with AVX-512 support.
Alongside Xeon 600, Intel is launching Core Ultra Series 3 (formerly known as Panther Lake) chips for businesses with vPro certification. The lineup is slimmer compared to the client Core Ultra Series 3 stack, but the specs are identical. The difference, of course, is Intel vPro support.
| Row 0 - Cell 0 | Core Ultra X9 388H | Core Ultra 9 386H | Core Ultra X7 368H | Core Ultra 7 366H | Core Ultra 7 365 | Core Ultra 5 338H | Core Ultra 5 336H | Core Ultra 5 335 | Core Ultra 5 332 |
Core Count (P + E + LP-E) | 16 (4 + 8 + 4) | 16 (4 + 8 + 4) | 16 (4 + 8 + 4) | 16 (4 + 8 + 4) | 8 ( 4 + 0 + 4) | 12 (4 + 4 + 4) | 12 (4 + 4 + 4) | 8 ( 4 + 0 + 4) | 8 ( 4 + 0 + 4) |
Max P-Core Frequency | 5.1 GHz | 4.9 GHz | 5 GHz | 4.8 GHz | 4.8 GHz | 4.7 GHz | 4.6 GHz | 4.6 GHz | 4.4 GHz |
Intel Smart Cache (L3 Cache) | 18MB | 18MB | 18MB | 18MB | 12MB | 18MB | 18MB | 12MB | 12MB |
NPU TOPS | 50 | 50 | 50 | 50 | 49 | 47 | 47 | 47 | 46 |
Graphics Brand | Arc B390 | Intel Graphics | Arc B390 | Intel Graphics | Intel Graphics | Arc B370 | Intel Graphics | Intel Graphics | Intel Graphics |
Xe Cores | 12 | 4 | 12 | 4 | 4 | 10 | 4 | 4 | 2 |
Platform PCIe Lanes (Gen 5 / Gen 4) | 12 (4 / 8) | 20 (12 / 8) | 12 (4 / 8) | 20 (12 / 8) | 12 (4 / 8) | 12 (4 / 8) | 20 (12 / 8) | 12 (4 / 8) | 12 (4 / 8) |
Thunderbolt | Four Thunderbolt 4 ports, Thunderbolt 5 support | Four Thunderbolt 4 ports, Thunderbolt 5 support | Four Thunderbolt 4 ports, Thunderbolt 5 support | Four Thunderbolt 4 ports, Thunderbolt 5 support | Four Thunderbolt 4 ports | Four Thunderbolt 4 ports, Thunderbolt 5 support | Four Thunderbolt 4 ports, Thunderbolt 5 support | Four Thunderbolt 4 ports | Four Thunderbolt 4 ports |
Wireless Connectivity | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 | Wi-Fi 7 R2, Bluetooth Core 6 |
Max Memory Speed and Capacity | 96GB LPDDR5x-9600 | 96GB LPDDR5x-8533 / 128GB DDR5-7200 | 96GB LPDDR5x-9600 | 96GB LPDDR5x-8533 / 128GB DDR5-7200 | 96GB LPDDR5x-7467 / 128GB DDR5-6400 | 96GB LPDDR5x-8533 | 96GB LPDDR5x-8533 / 128GB DDR5-7200 | 96GB LPDDR5x-7467 / 128GB DDR5-6400 | 96GB LPDDR5x-7467 / 128GB DDR5-6400 |
Base / Turbo Power | 25W / 65W, 80W | 25W / 65W, 80W | 25W / 65W, 80W | 25W / 65W, 80W | 25W / 55W | 25W / 65W, 80W | 25W / 65W, 80W | 25W / 55W | 25W / 55W |
Like the client stack, Core Ultra Series 3 processors with vPro support up to 96GB of LPDDR5 memory and up to 12 PCIe 5 lanes. The SoC is the first to use Intel’s 18A node on the compute tile, which combines Cougar Cove P-cores with Darkmont E-cores. The chips also come with Intel’s latest NPU 5 AI accelerator and an Xe3 iGPU with up to 12 cores. As we’ve seen with devices like the Asus Zenbook Duo, the iGPU is where Core Ultra Series 3 processors really earn their stripes, particularly the X-series models with the full 12 Xe3 cores.





You can see that from Intel’s internal benchmarks, as well. The Core Ultra X7 358H holds some victories over AMD’s competing Ryzen AI 9 HX PRO 375 in general productivity workloads, but it runs away with graphics performance. Intel also claims significantly higher AI performance in Geekbench AI 1.6. Keep in mind, however, that Geekbench is a pure benchmark; it isn’t a real-world workload.
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Intel details ‘all-new’ vPro platform
Both Xeon 600 and Core Ultra Series 3 chips for business support Intel’s updated vPro platform, which includes a handful of new features. For starters, Intel is expanding what vPro covers with the vPro Certified Apps and Accessories Program. As the name suggests, Intel is working with ISVs and OEMs to validate applications and accessories for vPro use. On the application side, Intel says vPro certification means apps are “optimized for battery life and performance,” while for accessories, they’re “certified for seamless connectivity.”
Through early engagements with ISVs, Intel says it’s seen up to a 59% reduction in CPU utilization in FlexxAgent (an endpoint application for centralized IT management) with vPro optimizations, a 56% improvement in power efficiency in Riverbed Aternity (an employee management platform), and a 74% reduction in background activity in Absolute Secure Endpoint. Alongside these applications, Intel says it has partnerships with ESET, Citrix, and Crowdstrike, among others, along with Dell, HP, Jabra, Lenovo, and Logitech on the accessories front.






Also new is Intel Device IQ, which is enabled through Lakeside, Riverbed, Control Up, and Flexxible software. Intel says Device IQ “collects PC telemetry, [and] uniquely applies local AI to trigger remediation directly on the device.”
On the security front, Intel has added its Total Storage Encryption (TSE) feature to vPro, alongside Intel Threat Detection Technology. The latter can detect malware in real-time using AI, says Intel. On the NPU, Intel announced support for CrowdStrike Falcon Data Protection, using the onboard AI capabilities to protect sensitive data during agentic AI workloads (we’ve certainly seen those workloads go wrong in the past). Finally, Intel is extending the servicing window for Core Ultra Series 3 machines with vPro to 10 years.
Intel says it has over 125 designs for Panther Lake machines that support vPro, including the usual names like Acer, Asus, Dell, and HP, alongside more commercial-focused OEMs like Fujitsu, Panasonic Connect, and Dynabook. Designs start rolling out on March 31.
Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

Jake Roach is the Senior CPU Analyst at Tom’s Hardware, writing reviews, news, and features about the latest consumer and workstation processors.
- Andrew E. FreedmanSenior Editor
-
bit_user Reply
Eh, not really. @JakeRoach , what they did was to create a suite of benchmarks that characterize different classes of applications, a little bit like SPEC benchmarks. However, they used open source software to construct the different benchmarks, even if they're a lot more niche than what programs end users would typically use to accomplish these tasks. So, they do try to model various stressful applications, even if it's a bit of an approximation.The article said:Keep in mind, however, that Geekbench is a pure benchmark; it isn’t a real-world workload.
In a few cases, like "Developer Workloads", the tools they use in the benchmarks are actually the same as what many people use. So, it's not simply an approximation in all cases.
All of this is documented here:
https://www.geekbench.com/doc/geekbench6-benchmark-internals.pdf
The main beef I have with Geek Bench is really their Multithreaded scores. The issue there is they didn't limit themselves to apps that scale well. So, the MT score doesn't increase very much, as you go beyond a relatively small number of cores. Many people (myself included) find this behavior surprising. It also means that just knowing what the GB6 MT score is won't necessarily indicate how well an app like rendering or compiling runs. As far as I'm concerned, the GB6 MT score is pretty much worthless. -
JakeRoach @bit_user In this case, we're looking at Geekbench AI, which is a bit different: https://www.geekbench.com/doc/geekbench-ai-workloads.pdfReply -
bit_user Do any of these support overclocking?Reply
Also, I find it annoying that none of the quad-channel models are available in retail boxed form. The 638 is the model most interesting to me, personally. Not that I'm in the market for one, but that's probably what I'd want, if I were. -
JakeRoach Reply
Yep! X-series SKUs support overclocking.bit_user said:Do any of these support overclocking? -
JamesJones44 Reply
Sadly, I feel like this is true for headline scores of all generalized benchmarks (ST and MT, MT being worse). That's why I don't like the way GB and others give a generalized "overall" score. If an application is not written to take advantage of multiple threads or the general app design simply can't accommodate multiple threads (UI heavy applications for example) then the MT score of a CPU doesn't tell how application Y will benefit.bit_user said:MT score is pretty much worthless.
Most RDBMSs for example love large CPU caches and high memory bandwidth, a GeekBench MT score might look great, but the CPU design has limit cache and low memory bandwidth which means the database a person is running might not improve performance wise much over a slower MT CPU with large cache/high memory bandwidth. Some show these types of stats in limited fashion, but are severely under represented IMO (I'm aware GB does test "cache misses" but this is just a single aspect of cache). While GB does test SQLite, SQLite is an embedded database with a limited query execution engine which is probably near the lowest end value wise database to use for general database benchmarking (don't get me wrong SQLite is a great DB, just don't expected to stress your system ever).
My view is, generalized benchmarks are great for comparing silicon A to silicon B's "raw" performance, but are not great at giving insight into how a particular application/game/OS/etc. might perform with the given CPU. -
thestryker Reply
While the question has already been answered there's so much platform information that isn't really publicized by Intel here: https://skatterbencher.com/2026/03/25/skatterbencher-99-intel-xeon-678x-overclocked-to-5300-mhz/bit_user said:Do any of these support overclocking?
Also, I find it annoying that none of the quad-channel models are available in retail boxed form. The 638 is the model most interesting to me, personally. Not that I'm in the market for one, but that's probably what I'd want, if I were.
The first one that made me pause is that the IMC ratios are fixed so RDIMMs run Gear 4 and MRDIMMs Gear 8. -
bit_user Reply
Pretty nice overclockability, but much less upside than Sapphire Rapids.thestryker said:While the question has already been answered there's so much platform information that isn't really publicized by Intel here: https://skatterbencher.com/2026/03/25/skatterbencher-99-intel-xeon-678x-overclocked-to-5300-mhz/