Intel officially releases Xeon 600 chips, announces new vPro Panther Lake CPUs — ‘all-new’ vPro platform goes all-in on AI

A one-sheet for Xeon 600.
(Image credit: Intel)

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.

Latest Videos FromTom's Hardware
Jake Roach
Senior Analyst, CPUs

Jake Roach is the Senior CPU Analyst at Tom’s Hardware, writing reviews, news, and features about the latest consumer and workstation processors.

With contributions from
  • bit_user
    The article said:
    Keep in mind, however, that Geekbench is a pure benchmark; it isn’t a real-world workload.
    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.

    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.
    Reply
  • 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.pdf
    Reply
  • bit_user
    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.
    Reply
  • JakeRoach
    bit_user said:
    Do any of these support overclocking?
    Yep! X-series SKUs support overclocking.
    Reply
  • JamesJones44
    bit_user said:
    MT score is pretty much worthless.
    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.

    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.
    Reply
  • thestryker
    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.
    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/
    The first one that made me pause is that the IMC ratios are fixed so RDIMMs run Gear 4 and MRDIMMs Gear 8.
    Reply
  • bit_user
    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/
    Pretty nice overclockability, but much less upside than Sapphire Rapids.
    Reply