Nvidia Unveils RTX Pro 6000 Blackwell: A Powerhouse GPU for AI and Professional Workloads

Nvidia's RTX Pro 6000 has 96GB of VRAM and 600W of power

Tom Warren is a senior editor and author of Notepad, who has been covering all things Microsoft, PC, and tech for over 20 years. Nvidia is announcing its RTX Pro Blackwell series of GPUs today, designed to meet the needs of professional designers, developers, data scientists, and creatives. The lineup includes a top of the line RTX Pro 6000 Blackwell GPU for workstations, as well as other RTX Pro Blackwell desktop and laptop variants and a datacenter version of the RTX Pro 6000 Blackwell. The RTX Pro 6000 Blackwell for workstations will ship with 96GB of GDDR7 memory and needs 600 watts of power, slightly more than the 575 watts of the RTX 5090. It also includes PCIe Gen 5 support, DisplayPort 2.1, and the latest Blackwell generation of RT cores and Tensor cores. This GPU is designed for workstation use, aimed primarily at professionals that work on game development, AI workloads, or any professional tasks that need a lot of VRAM and a fast GPU. The RTX Pro 6000 Blackwell will also be available in a Max-Q variant and a server edition for datacenters. Nvidia is using its new RTX Pro branding to replace the RTX numbering scheme it has used previously, as well as Quadro in the past. Nvidia is also launching the RTX Pro 5000 and RTX Pro 4000 Blackwell in desktop and laptop form factors, alongside the RTX Pro 4500 Blackwell for desktops. Laptop versions of the RTX Pro Blackwell will also include the 3000, 2000, 1000, and 500 models. The laptop variants come with up to 24GB of VRAM, and these GPUs also support Nvidia's latest Blackwell Max-Q technologies that the company claims will "intelligently and continually optimize laptop performance and power efficiency with AI." These laptop GPUs will also challenge AMD's Strix Halo chips that have 128GB of unified memory that is shared among the CPU, GPU, and AI engines. Framework has built a tiny desktop with AMD's latest chips, so it will be interesting to see what kind of workstations and laptops will ship with Nvidia's RTX Pro Blackwell GPUs. Nvidia hasn't put a price on the RTX Pro 6000 workstation variant just yet, but this GPU will be available from distribution partners like PNY and TD Synnex in April, with availability from manufacturers like Dell, HP, and Lenovo starting in May. The server variant will be available from Cisco, Dell, HP, Lenovo, and Supermicro "soon." Cloud providers like AWS, Google Cloud, Microsoft Azure, and CoreWeave will also have RTX Pro 6000 Blackwell servers later this year. The rest of the RTX Pro Blackwell lineup for workstations will be available in the summer from Boxx, Dell, HP, and Lenovo, and the RTX Pro Blackwell laptop variants will ship in Dell, HP, Lenovo, and Razer devices later this year.

Nvidia RTX Pro 6000 up close: Blackwell RTX Workstation, Max-Q Workstation, and Server variants shown

The Nvidia Blackwell RTX Pro 6000 GPU was announced during the GTX 2025 keynote. These will use the same GB202 die that goes into Nvidia's RTX 5090 graphics card, but with some significant changes in some of the other aspects. There will be three variants of the RTX Pro 6000: the Blackwell Workstation Edition, Max-Q Workstation Edition, and Blackwell Server Edition. The core specifications for the RTX Pro 6000 are the same across all three models. You get 188 SMs enabled, out of a potential 192 maximum from GB202. That's 10.6% more SMs, shader cores, tensor cores, RT cores, etc., relative to the RTX 5090. Clock speeds weren't given, but Nvidia does list up to 125 TFLOPS of FP32 compute via the shaders, and 4000 AI TOPS from the tensor cores. That works out to a boost clock of around 2.6 GHz, but that won't be the same for all three variants. The RTX Pro 6000 features the full 128MB L2 cache of GB202, along with four NVENC and four NVDEC video blocks. RTX 5090 only has 96MB of L2 cache and three each for NVENC/NVDEC. It's very close to a fully enabled chip, with only 2% of the SMs disabled. The Blackwell Workstation Edition looks basically the same as the RTX 5090, except with a glossy black finish in places rather than a matte black. TDP (TGP) for the card is 600W, 25W higher than the 5090, but otherwise, the two cards look about the same. You also get four DisplayPort 2.1b outputs, whereas the 5090 typically offers at least one HDMI 2.1b output. For the Max-Q Workstation Edition, the TGP gets capped at 300W. Half the power will naturally mean lower typical boost clocks for a lot of workloads, though there will undoubtedly be cases where it will still run nearly as fast as the 600W card. It also has a standard FHFL (full-height, full-length) dual-slot form factor with dual-blower fans at the back of the card. It also has four DP2.1b outputs. Finally, the Blackwell Server Edition has a similar form factor to the Max-Q card but ditches the fans, instead relying on the server fans to provide airflow and cooling. That's usually in ample supply for servers, and noise levels are usually less of a concern -- you get high RPM fans moving lots of air in a regulated environment to make everything run sufficiently cool. The power on the Server Edition is configurable up to 600W, so some installations might opt for lower power to optimize the efficiency if they're power-limited. All three models use the same 16-pin connector found on desktop RTX cards. Servers and workstations tend to be built to much tighter specifications, and so far there haven't been any widespread reports of servers or workstations with melting connectors. That suggests perhaps that the biggest issues with 16-pin connectors are component quality and proper installation -- companies are less likely to cheap out on the cables in a server or workstation, so there aren't impurities causing hot spots and melting. Pricing hasn't been discussed, but we typically see professional and server solutions like the RTX Pro 6000 selling for 4X~5X more than the equivalent consumer GPUs. It wouldn't be surprising if the various RTX Pro 6000 cards cost $10,000 or more. We'll find out exactly where they fall in the coming days.

Nvidia launches its fastest GPU ever: Nvidia RTX Pro 6000 Blackwell Workstation Edition is an enhanced version of the RTX 5090 with more of everything

Based on the Blackwell architecture, the newcomers use the RTX Pro moniker to differentiate themselves from the previous generations (Ada Lovelace, Ampere, and Turing) and, from their consumer breathens. The flagship models are three RTX Pro 6000 Blackwell GPU variants with 96GB ECC GDDR7 memory and up to 4000 AI TOPS performance - twice the amount of memory in its former performance champion, the RTX 6000 and a staggering 4x the RTX 5090, the best GPU on the consumer market has to offer. Nvidia GPU launches Alongside the standard Workstation Edition, Nvidia also introduced the Blackwell Max-Q Workstation Edition and the Server Edition. The latter is the successor to the L40 Data Center GPU series, bringing some much-needed consistency to the GPU nomenclature. As for the Max-Q Workstation Edition, it remains a bit of a mystery. Nvidia launched Max-Q technology back in 2017 and this is usually associated with laptop GPUs trying to achieve maximum efficiency. However, workstation PCs rarely aim for optimal energy consumption except perhaps in power-constrained environments like small form factor mini PCs. Three other professional desktop GPUs were also introduced: the Pro 5000, Pro 4500 and Pro 4000, which will be available starting May 2025. Given past product launch cycles, I expect more models focusing on the entry-level and mainstream parts of the market, to be launched by the end of 2025. Six new laptop GPUs were also launched, all of them carrying the RTX Pro naming convention and, confusingly enough, some having the same name as their desktop counterparts. The RTX Pro 5000 Blackwell is the new laptop flagship GPU with 24GB ECC GDDR7 memory; other models include the 4000, 3000, 2000, 1000, and 500 series and should directly replace their respective "Ada Generation" part. All these parts will be available from OEM partners in mobile workstations starting in June 2025. We'll strive to update this article when further details of the cards (including pricing) are published. Nvidia's GTC Keynote also saw the formal launch of DGX Spark, formerly known as Project Digits, the DGX station and Blackwell Ultra (or GB300), Nvidia's most powerful GPU ever.

Nvidia RTX Pro 6000 Blackwell sets a new standard for workstation GPUs

Nvidia announced a host of new GPUs at its GTC 2025 conference on Tuesday, including the RTX Pro Blackwell series. The highlight component of the series is the RTX Pro 6000 Blackwell GPU, developed for workstations. The RTX Pro 6000 Blackwell GPU is also available in variants to support desktops, laptops, and data centers. The component is intended to aid professional designers, developers, data scientists, and creatives, the Verge noted. The RTX Pro naming sequence allows the Blackwell-based GPU to stand out against previous architectures, including Ada Lovelace, Ampere, and Turing, as well as the standard consumer product GPUs, Tech Radar Pro noted. Recommended Videos Specifications for the RTX Pro 6000 Blackwell for workstations include 96GB of GDDR7 memory and up to 4000 AI TOPS performance. The GPU requires 600 watts of power, making it slightly more powerful than the consumer-tier RTX 5090 GPU. Get your weekly teardown of the tech behind PC gaming ReSpec Subscribe Check your inbox! Privacy Policy With a similar design to the high-end gaming GPU, the RTX Pro 6000 Blackwell features a double-flow-through cooling system. It also includes 24,064 CUDA cores, a 512-bit memory bus, and 1792 GB/s of memory bandwidth. Output includes PCIe Gen 5 support, DisplayPort 2.1, as well as updated software support for the latest Blackwell generation of RT cores and Tensor cores. Nvidia noted the RTX Pro 6000 Blackwell workstation will be used in many high-performance sectors, including generative AI, game development, cloud services, architecture, automotive, financial services, healthcare, manufacturing, media and entertainment, and retail. The Verge also confirmed that the GPU will be available in a Max-Q Workstation Edition, indicating a "maximum efficiency" variant. The platform will also have an RTX Pro 6000 Blackwell Server Edition. Nvidia also confirmed other naming sequences, including the RTX Pro 5000 and RTX Pro 4000 Blackwell for desktops and laptops and the RTX Pro 4500 Blackwell for desktops. These options will be available in May. Nvidia has not yet indicated a price for the RTX Pro 6000 workstation variant; however, the brand has shared some partner details- including PNY and TD Synnex, and manufacturer information including Dell, HP, and Lenovo. These companies should be releasing the component respectively by April and May. Other variants and partners have less succinct information with availability expected between the summer and later in the year.

NVIDIA introduces RTX PRO 6000 'Blackwell' GPU series: 24064 cores, 96GB memory and up to 600W

TL;DR: NVIDIA's new RTX PRO 6000 "Blackwell" graphics card features a GB202 GPU with 24,064 cores and 96GB of GDDR7 memory, offering a 19% performance increase over the RTX 5090. It supports 600W TDP, 4000 AI TOPs, and 125 TFLOPS of FP32 compute performance. The card excels in memory capacity and AI workloads. NVIDIA has just unveiled its new RTX PRO 6000 "Blackwell" graphics card, based on the same GB202 GPU and GDDR7 memory that the RTX 5090 uses, but with a whopping 96GB of GDDR7 memory. The new NVIDIA RTX PRO 6000 Blackwell GPU features the GB202 GPU with 24,064 cores inside of 188 SMs, compared to the 21,760 cores and 170 SMs inside of the same GB202 GPU in the GeForce RTX 5090. The full-fat GB202 GPU features 192 SMs, so we're not even maxed out here with the new RTX PRO 6000. We do have the full 600W of TDP support through a single 12V-2x6 power connector, offering 25W more TDP than the 575W on the RTX 5090. With all of this in tow, NVIDIA's new RTX PRO 6000 Blackwell GPU features 4000 AI TOPs, 125 TFLOPS of FP32 compute performance, and 380 TFLOPS of RT performance (a 19% increase over the RTX 5090 in all performance figures). Not only do we have a beefier GB202 GPU, but that 19% increase on GPU specs over the RTX 5090 are far more visible on the RTX PRO 6000 Blackwell GPU when it comes to memory capacity. NVIDIA's consumer-focused GeForce RTX 5090 features 32GB of GDDR7 memory, but the new RTX PRO 6000 Blackwell GPU has a far larger 96GB pool of GDDR7 memory: a 3x increase. We have the same 512-bit memory bus and same 28Gbps GDDR7 memory modules, with 1792GB/sec of memory bandwidth in total. NVIDIA is using the same double-flow-through design and dual-slot form factor, supporting MIG (Multi-Instance-GPU) capability with 4 x 24GB, 2 x 48GB, or 1 x 96GB modes. Our friends over at Wccftech have obtained some new benchmark figures using GameTechBench, with the new benchmark (available on Steam) featuring full path tracing (CGI rendering) and provides a good look into the more powerful GB202 GPU + 96GB of GDDR7 memory We have a 5% performance lead at 4K in the GameTechBench over the RTX 5090, with the RTX PRO 6000 GPU just behind in 1440p real-time ray tracing tests. In the offline Path Tracing rendering mode, the new NVIDIA RTX PRO 6000 Blackwell GPU is only 2% faster than the RTX 5090. It will be interesting to see if we have 19% performance uplifts in full AI workloads, especially with that far larger 96GB pool of GDDR7 memory, a 3x increase in VRAM capacity over the 32GB on the RTX 5090.

Nvidia RTX Pro Blackwell series pack insane power for AI and 3D work

Nvidia announced the RTX Pro Blackwell series of GPUs, including the RTX Pro 6000 Blackwell for workstations, designed for professional workloads across various industries. The launch occurred during the GTC event. The RTX Pro 6000 Blackwell for workstations features 96GB of GDDR7 memory and requires 600 watts of power, slightly more than the 575 watts of the RTX 5090. It includes double flow-through cooling, 24,064 CUDA cores, a 512-bit memory bus, and 1792 GB/s of memory bandwidth. The GPU supports PCIe Gen 5, DisplayPort 2.1, and includes the latest Blackwell generation of RT and Tensor cores. This GPU is specifically tailored for professionals working in areas such as game development, AI workloads, and tasks that necessitate substantial VRAM and high-processing speed. The RTX Pro 6000 will also be available in a Max-Q variant and a server edition for data centers. Nvidia is adopting the new RTX Pro branding, which replaces both the RTX numbering scheme and previous Quadro branding. The lineup also includes the RTX Pro 5000 and RTX Pro 4000 Blackwell for desktops and laptops, along with the RTX Pro 4500 Blackwell for desktops. Laptop versions of the RTX Pro Blackwell will consist of the 500, 1000, 2000, 3000, and 4000 models, offering up to 24GB of VRAM. These variants support Nvidia's latest Blackwell Max-Q technologies, aimed at optimizing laptop performance and power efficiency using AI. They will compete against AMD's Strix Halo chips, which have 128GB of unified memory shared among the CPU, GPU, and AI engines. Nvidia has yet to disclose pricing for the RTX Pro 6000 workstation variant. It will be available through distribution partners such as PNY and TD Synnex in April, with manufacturers like Dell, HP, and Lenovo offering it starting in May. The server variant will be accessible from Cisco, Dell, HP, Lenovo, and Supermicro in the near future, with cloud providers including AWS, Google Cloud, Microsoft Azure, and CoreWeave expected to provide RTX Pro 6000 Blackwell servers later this year. RTX Pro Blackwell GPUs unlock advanced capabilities in generative, agentic, and physical AI, delivering high performance and efficiency. Key features include: The RTX Pro 6000 data center and server editions are optimized for enterprise deployments and can support up to eight GPUs per server. This configuration allows for high-performance solutions in AI, scientific computing, and visual computing across industries such as healthcare and manufacturing. Nvidia vGPU™ software will be available for the RTX Pro 6000 Blackwell Server Edition in the latter half of the year, allowing for the powering of AI workloads across virtualized environments. Availability of the RTX Pro 6000 Blackwell is expected from leading data center partners and cloud service providers later this year. The RTX Pro 6000 Blackwell Workstation and Max-Q editions will be shipped from April and May, respectively, with other workstation editions and laptop variants rolling out throughout the summer.

NVIDIA's new RTX PRO 6000 Blackwell GPU with 96GB GDDR7 costs $8435, should launch in May

TL;DR: NVIDIA's RTX PRO 6000 Blackwell GPU, priced at $8435-$8565, features 96GB GDDR7 memory, 24,064 cores, and 600W TDP. NVIDIA's new beefed-up RTX PRO 6000 Blackwell GPU has turned up on US-based IT reseller Connection, with a price of $8435 (if you buy it in bulk) or $8565 (boxed). The new NVIDIA RTX PRO 6000 Blackwell GPU comes with a huge 96GB of GDDR7 memory, 3x the GDDR7 memory that the new gaming flagship GeForce RTX 5090 has. There are a couple of different RTX PRO 6000 Blackwell GPUs, with the RTX PRO 6000 Blackwell Workstation Edition, and the RTX PRO 6000 Blackwell Max-Q Workstation Edition. The difference here is that the Max-Q variant is capped at 300W, while retaining 88% of its AI performance according to NVIDIA. NVIDIA's upcoming RTX PRO 5000 Blackwell GPU will launch with 48GB of GDDR7 memory and a price between $4439 and $4569, while the RTX PRO 4500 comes with 32GB, and the RTX PRO 4000 with 24GB. The new NVIDIA RTX PRO 6000 Blackwell GPU features the GB202 GPU with 24,064 cores inside of 188 SMs, compared to the 21,760 cores and 170 SMs inside of the same GB202 GPU in the GeForce RTX 5090. The full-fat GB202 GPU features 192 SMs, so we're not even maxed out here with the new RTX PRO 6000. We do have the full 600W of TDP support through a single 12V-2x6 power connector, offering 25W more TDP than the 575W on the RTX 5090. With all of this in tow, NVIDIA's new RTX PRO 6000 Blackwell GPU features 4000 AI TOPs, 125 TFLOPS of FP32 compute performance, and 380 TFLOPS of RT performance (a 19% increase over the RTX 5090 in all performance figures). We have the same 512-bit memory bus and same 28Gbps GDDR7 memory modules, with 1792GB/sec of memory bandwidth in total. NVIDIA is using the same double-flow-through design and dual-slot form factor, supporting MIG (Multi-Instance-GPU) capability with 4 x 24GB, 2 x 48GB, or 1 x 96GB modes.

Nvidia RTX PRO 6000 Blackwell Series with 96GB VRAM Unveiled

Nvidia confirmed the full RTX PRO lineup will be available by the end of this summer. Nvidia's latest Blackwell series extends as the chip giant reveals the PRO lineup today. The flagship prosumer card, RTX PRO 6000 "Blackwell," is based on the GB202 GPU with the same architecture. However, the Nvidia RTX PRO 6000 for workstations has 96GB of GDDR7 memory. Remember that the RTX 5090 offers 32GB of VRAM and runs on 575 watts of power. Compared to this, the RTX PRO card for workstations will require 600 watts of power. With a GB202 chip containing 24,064 CUDA cores, the RTX PRO 6000 advances in AI workloads and ray tracing, offering 125 TFLOPS FP32 and 4000 TOPS of AI performance at FP4 precision. Its 96GB GDDR7 ECC memory, a significant upgrade from the RTX 5090's 32GB, delivers a massive 1.8 TB/s of memory bandwidth for demanding professional applications. The RTX PRO lineup includes a Max-Q variant and a server edition for data centers. The RTX PRO 6000, targeting professionals in game development, AI, and demanding VRAM-intensive tasks, debuts Nvidia's new RTX PRO branding, replacing previous RTX/Quadro naming. Alongside, Nvidia introduces RTX PRO 5000, 4500, and 4000 Blackwell GPUs for desktops and laptops. Laptop RTX PRO models (3000-5000) offer up to 24GB VRAM and feature Blackwell Max-Q for AI-driven power efficiency. These GPUs compete with AMD's Strix Halo unified memory architecture, setting the stage for new workstation and laptop designs. The RTX PRO workstation series does not yet have a price tag. As for availability, Nvidia confirmed that the RTX PRO 6000 Blackwell Server Edition will soon be available in server configurations from leading data center partners, including Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo, and Supermicro. Moreover, Cloud providers and data center partners will offer RTX PRO 6000 Server Edition instances later this year. Workstation RTX PRO 6000 models launch in April via distributors and May via manufacturers. Other RTX PRO Blackwell GPUs will arrive this summer (desktops) and later this year (laptops) through various partners. Are you excited about the Nvidia RTX PRO 6000 card? Do you think it will go past the RTX 5090 bricking issues? Share your thoughts in the comments below.

NVIDIA RTX PRO 6000 "Blackwell" Series Launched: Flagship GB202 GPU With 24K Cores, 96 GB VRAM, Up To 600W TDP

NVIDIA has officially launched its RTX PRO 6000 "Blackwell" series of GPUs aiming at the presumer and server segment with loads of power. NVIDIA Rolls Out RTX PRO 6000 "Blackwell" GPUs With Tons of Compute Capabilities & Massive 96 GB VRAM Today, NVIDIA introduces its next-generation Prosumer, Data Center, and AI-specialized graphics card, the RTX PRO 6000 "Blackwell". This monster of a graphics solution comes with even more compute power than the gaming RTX 5090. The card will be available in three variants, starting with the standardized design along with a Max-Q and server flavor, depending on the demands of the consumers. The NVIDIA RTX PRO 6000 "Blackwell" will have 24,064 cores, 10.5% more than the RTX 5090's 21,760 cores. In addition to the core count, the chip will also pack 752 tensor cores and 188 RT cores. The card will offer up to 125 TFLOPs of FP32 and 4000 AI TOPS worth of performance. But the biggest upgrade over the RTX 5090 will be its insane memory capacity. Unlike the NVIDIA GeForce RTX 5090, which features 32 GB GDDR7 memory across a 512-bit bus interface, the RTX PRO 6000 "Blackwell" will get 96 GB of GDDR7 (ECC) memory across the same 512-bit bus. The graphics cards will be configured at 28 Gbps speeds, delivering up to 1.8 TB/s of total bandwidth. As for the TBP, the NVIDIA RTX PRO 6000 will be rated at 600W, which is the full capacity allowed by a single 12V-2x6 16-pin power interface. Cooling such a beastly card would require loads of work and NVIDIA's thermal engineering team has repurposed the dual-fan and dual-slot cooler to meet the needs of this card. But this is the cooling for the standard variant. The other two variants will serve different needs. The RTX PRO 6000 "Blackwell" Max-Q will come with a blower-style design and is aimed at the work-station segment, with its dual-slot and blower-fan design. The other variant is designed for server environments and will use a passive cooling solution. The Max-Q variant will operate at a TDP of 300W. Lastly, in terms of pricing, expect this workstation behemoth to cost anywhere around $10-$15K or even higher. Canadian retailer Direct Dial is currently listing the card for CAD 11,933 or around $8300 US. This is over four times more than the RTX 5090's MSRP, though in reality, the RTX 5090 costs around $3000 US, which still makes the RTX PRO 6000 "Blackwell" over two times more expensive.