Anyone wondering what is filling up their GPU's VRAM can now try gputaskman, a free, open-source tool from Microsoft VP Scott Hanselman. It runs in a terminal window with an htop-style layout and lists every process using the GPU with its memory footprint, engine activity, and loaded runtime, such as CUDA or Vulkan. A panel up top tracks utilization, clocks, temperature, and power. Hanselman shared the project on X last week and asked for pull requests.

Task Manager has shown GPU usage since 2017, and it will happily tell you that 15 GB of video memory is in use. It just won't say what is using it. gputaskman goes after that gap with a heavy focus on local AI. Its model inspector can identify the LLM a process has loaded and report its quantization, weights, and estimated KV cache cost, while Ollama and LM Studio users also get context size and proper model names. Hanselman calls it early, experimental software, and the AI breakdowns are estimates for now.

Gigabyte today announced the launch of AI TOP AERO, a new AI desktop powered by the NVIDIA RTX Spark platform. Positioned as a Personal AI Studio, AI TOP AERO combines an NVIDIA Blackwell architecture GPU, up to 128 GB of unified system memory, and Gigabyte's cooling and compact chassis design. The new desktop expands Gigabyte's AI PC lineup, bringing local AI development, content creation and gaming to personal workspaces.

NVIDIA RTX Spark unites NVIDIA AI, RTX graphics, and unified memory in one slim, powerful Windows PC. Designed to run larger AI models locally--without cloud dependency--and move between creative work, development, and immersive gaming without missing a beat. Connect apps, tools, and workflows into one seamless experience. Private by default. RTX Spark brings NVIDIA's full-stack AI platform, ready for the AI workloads of today and whatever comes next. Delivered on the familiar, trusted Windows platform.

NVIDIA has released NVIDIA App 11.0.9.585, a small update that adds DLSS Override profiles for 19 games and Optimal Settings profiles for six. The list mixes older titles like PUBG: Battlegrounds, The Witcher 3: Wild Hunt, and Dragon's Dogma 2 with Control Resonant, Silent Hill: Townfall, Ace Combat 8: Wings of Theve, Gears of War: E-Day, and Star Wars: Galactic Racer, all of which were scheduled to launch in September or October. Oddly enough, 007 First Light was already listed in the main 11.0.9 release, and Active Matter showed up back in 11.0.8. NVIDIA doesn't explain the repeats, and it doesn't say which overrides each game supports either.

The changelog otherwise only mentions "various stability/security fixes" without any details. This build follows two bigger ones that added significantly more features. The main 11.0.9 release brought DLSS 4.5 Ray Reconstruction and per-game Resizable BAR controls, while 11.0.9.565 added RTX Spark support, a local MCP server for AI agents, and a faster Performance Mode for DLSS Frame Generation. As a refresher, DLSS Override lets GeForce RTX owners use newer DLSS models, or modes like DLAA, that a game may not offer on its own. It sits under Graphics > Program Settings > Driver Settings. Below is the full list of games.

NVIDIA today released the latest version of GeForce Game Ready drivers. Version 621.14 WHQL comes with optimization for "World of Warcraft: Forever," and the new Slaughter Mode of "DOOM: The Dark Ages Revelations." The drivers also introduce support for DLSS 5 with 3D-guided Neural Rendering for "Hogwarts Legacy" and "War Thunder" on GeForce RTX 50-series GPUs. Among the gaming bugs fixed with this release are incorrect visual colors displayed in "Call of Duty: Modern Warfare 4." Among the general bugs fixed are an issue seen where video playback freezes or turns black on some GeForce RTX 50-series GPUs or RTX Spark processors after updating to driver version 621.01. Grab the driver from the link below.

DOWNLOAD: NVIDIA GeForce 621.14 WHQL

NVIDIA is bringing its DLSS 5 neural rendering technology to three more games this month, starting with Hogwarts Legacy on November 5. According to NVIDIA, War Thunder will follow in mid-November, while Where Winds Meet is scheduled to receive support on November 23. NVIDIA is also bringing DLSS 4.5 to several games, and has updated DLSS 4.5 Unreal Engine plugin. NVIDIA was also keen to note that its October 2026 update has significantly reduced the footprint, decreased VRAM usage, and increased performance.

DLSS 5 introduces what NVIDIA calls 3D-Guided Neural Rendering, using AI to enhance lighting, shadows and material details based on information from the game engine. The technology operates as a final rendering stage, using the original frame, geometry, textures and lighting data as its foundation. According to NVIDIA, this approach allows developers to introduce more realistic lighting and material effects without having to explicitly model and render all the additional detail. The company also provides developers with controls to adjust how the technology affects individual scenes, objects and characters, using different AI models, intensity settings and semantic masking to preserve the original artistic direction.

Today, at 7pm PT, the much-anticipated Phantom Blade Zero launches with DLSS 4.5, ray tracing and path tracing, playable on GeForce RTX and RTX Spark. The Blood of Dawnwalker can now be upgraded to DLSS 4.5 Super Resolution and Dynamic Multi Frame Generation via the NVIDIA app.

NVIDIA RTX Remix 1.6 has been added to the Half-Life 2 RTX demo and Portal with RTX, introducing support for DLSS 3D-Guided Neural Rendering, and upgrading DLSS Ray Reconstruction and DLSS Frame Generation with our latest AI models. And our beta RTX Remix mod for Minecraft: Java Edition has been released.

Microsoft has rolled out the first firmware update for its RTX Spark-powered Surface Laptop Ultra, less than a week after the laptop started shipping on October 16. Listed in Windows Update as "System Hardware Update 200.0.7.0," the October 22 release fixes three problems spelled out in Microsoft's update history: extended reboot times, screen flickering, and unexpected restarts. It also bundles unspecified bug fixes and general performance improvements. The update is arriving in stages, so not every owner will see it right away, and like other Surface firmware, it can't be rolled back once installed.

These issues had already surfaced in early reviews and owner reports. Windows Central noted reboots long enough to roughly double the time it took to install updates, while some owners saw the Mini-LED panel flicker, in a few cases only when the display sat idle. However, the update doesn't address everything reviewers flagged. Notebookcheck measured a sluggish 57 ms black-to-white response time with visible ghosting, no local dimming, and a grayish 0.61-nit black level, and it seems unlikely that firmware can do much about those. Some owners have also reported the laptop running hot under light workloads, which Microsoft hasn't mentioned.

NVIDIA has released version 1.9.0 of RTX Path Tracing (RTXPT), its open-source reference path tracer on GitHub, claiming roughly 20% better performance than the previous 1.8.1 release, with comparable or better image quality. RTXPT is a code sample for developers, meant as a starting point for building a path tracer or as a reference for NVIDIA's other ray tracing SDKs. Several changes add up to that uplift. The path tracer can now optionally trace only three quarters, half, or a quarter of the pixels each frame, and the built-in performance presets use this by default, along with lower bounce limits in the faster modes.

On DirectX 12, async compute lets the previous frame's DLSS Ray Reconstruction and post-processing overlap with the next frame's path tracing, and TLAS instance generation has moved to the GPU. Lighting got some attention too. NEE-AT light sampling now handles up to 2 million lights, up from 512K, and the SHaRC radiance cache is on by default in real-time mode, apparently feeding more indirect lighting into DLSS Ray Reconstruction at about the same cost. Version 1.9 also adds Windows on ARM64 support. The release notes don't say why, though it's probably no coincidence, given NVIDIA's own Arm-based RTX Spark chip for Windows PCs.

GeForce RTX GPUs accelerated by DLSS 4.5 give you the definitive experience in the wealth of top-rated games that have recently launched, and new titles such as Call of Duty: Modern Warfare 4, Crimson Desert Enhanced: Charting the Unknown and Phantom Blade Zero.

On October 16th, Call of Duty: Modern Warfare 4 Campaign Early Access began, followed by DMZ Early Access yesterday. On the 23rd, the full game officially arrives with the addition of multiplayer, and using our latest Game Ready Driver you can optimize your experience with DLSS 4.5 and Advanced Shader Delivery.

NVIDIA's new DLSS Frame Generation Preset C has only been out for a few days, and modders have already brought it to RTX 30 cards. The latest version of dashdogy's Universal MFG Unlocker (v1.5.0, formerly RTX 40 MFG Unlock) adds Preset C support on both RTX 40 and RTX 30 GPUs, including 3x to 6x multi-frame generation (MFG). Officially, Preset C is a beta "performance mode" for RTX 40, RTX 50, and RTX Spark systems, available through the NVIDIA app's experimental features. It swaps one of Frame Generation's two AI models, the one handling optical flow, for a lighter algorithm, and NVIDIA claims up to 35% higher performance in exchange for a small hit to image quality.

According to the release notes, RTX 30 support is now considered stable, with smoother frame pacing at 3x and above, though it only works in DirectX 12 games. However, the newest DLSS Frame Generation build that carries Preset C has only been validated offline on RTX 30, and the preset was confirmed in-game on an RTX 40 card in The Witcher 3. No RTX 30-series performance numbers have been shared yet, so the gains on Ampere are anyone's guess. The update also adds XeSS Multi Frame Generation from 2x to 6x on NVIDIA, AMD, and Intel GPUs through an OptiScaler plugin, and fixes a launch crash in Gears of War: E-Day. This effort follows recent mods that got DLSS Multi Frame Generation running on Ampere and also brought Smooth Motion to the same cards.

NVIDIA today announced the availability of NVIDIA RTX Spark laptops, bringing together RTX graphics and NVIDIA's full-stack AI platform in slim, premium Windows PCs for accelerated creation, immersive gaming and powerful local AI—rolling out from ASUS, Dell, HP, Lenovo, Microsoft and MSI.

Combining decades of NVIDIA innovation into a single superchip, RTX Spark delivers up to 128 GB of unified memory and 1 petaflop of FP4 AI performance to run large language models and AI agents locally. On a single device, creators, developers and gamers can move seamlessly between their everyday workflows and emerging AI agents on the familiar Windows platform.

ASUS today announced that the ProArt P16 and P14 laptops, powered by NVIDIA RTX Spark, are now available for purchase in Canada, with select configurations shipping starting today through the ASUS Store, Amazon Canada, Best Buy Canada, Memory Express and Newegg Canada. Purpose-built for creators, AI developers and workflow builders, these Windows PCs combine high-capacity unified memory, an NVIDIA Blackwell RTX GPU and an NVIDIA Grace CPU to support demanding local AI and creative workloads. The NVIDIA CUDA ecosystem and an expanding ASUS-exclusive agent-and-application solution make local AI easier to deploy, personalize and use, with the flexibility to connect cloud services when needed.

Together, Hermes Agent and ComfyUI deliver a compelling local-first, cloud-flexible AI experience. By bringing industry-validated workflows and agent-connected creative tools to users' own PCs, they enable generative AI creation and AI-assisted development, with the flexibility to integrate cloud services when needed.

NVIDIA today announced that its new RTX Spark superchip that will power the next-generation of AI-native PCs, will be Game Ready for dozens of AAA games at launch on Windows 11, providing an uncompromising gaming experience that's maxed out for 1440p. The RTX Spark superchip features a 20-core Grace CPU and a GeForce RTX Blackwell iGPU featuring 6,144 CUDA cores. NVIDIA is closely collaborating with Microsoft and the various game developers to ensure not just Spark-native ports of popular titles, but also seamless translation of games to the RTX Spark platform for both the system- and graphics APIs.

A key announcement here is that NVIDIA is working with developers of competitive online games to ensure that their anti-cheat solutions work seamlessly with RTX Spark. Modern anti-cheat solutions rely heavily on kernel-mode interactions with hardware to ensure trust, something that has the potential to break in scenarios where games originally developed for Windows x64 machines are made to run on Windows Arm64 machine through translation layers. NVIDIA's developer collaboration ensures that the hardware-end of the anti-cheat trust-chain remains intact, and you should be able to play your favorite online games such as Counter-Strike 2, Dota 2, Fortnite, Marvel Rivals, NARAKA: BLADEPOINT, Rocket League, RUST, THE FINALS, War Thunder, World of Tanks, and more.

NVIDIA has updated its DLSS Frame Generation algorithm to be faster and more efficient. In the latest NVIDIA App beta update, rolling out today, the company introduced "Preset C," the fastest Performance Mode for DLSS Frame Generation. NVIDIA demonstrates that this mode can make frame generation up to 35% faster on the GeForce RTX 5060, with minimal trade-offs in image quality. This improvement applies to the GeForce RTX 40-Series, GeForce RTX 50-Series, and RTX Spark.

According to NVIDIA, there are two models for DLSS: Multi-Frame Generation and Frame Generation. The first model uses a standard AI approach that inputs motion vectors and depth to understand how two rendered frames are constructed. The second model employs optical flow for in-game elements like UI and ray tracing. Today, NVIDIA replaced this optical flow model with a much faster and lighter AI algorithm that boosts FPS across DLSS Frame Generation, Multi-Frame Generation, and Dynamic Multi-Frame Generation. This new model is available for download through the NVIDIA App beta update, so ensure you're running the latest beta version to try out the "Preset C" setting.

NVIDIA is marking the retail launch of its RTX Spark laptops with a public party in Berlin, and anyone aged 18 or older can attend. The RTX Spark Launch Celebration takes place on October 16, the same day the first laptops ship, at XPERION on Alexanderplatz. NVIDIA is presenting it as "a new beginning for Windows PCs" in the run-up to GTC Berlin, and the evening combines a stage program with hands-on demo stations and a laptop raffle. The company is even lighting up the Berlin TV Tower in NVIDIA green for the occasion.

Entry is free, although registration through Luma is required beforehand. The queue opens at 18:00 local time and doors open at 18:45. XPERION sits inside the Saturn store at Alexanderplatz 3, and capacity is limited, especially for the stage show. NVIDIA recommends arriving early for that reason, since that is how visitors secure entry, a spot in the raffle, and a goodie bag. The Berlin event is a chance to try RTX Spark hardware in person, across AI, creative, and gaming workloads.

Microsoft says "hundreds" of AAA and indie games will run on NVIDIA RTX Spark PCs from day one, though Call of Duty will not be one of them. Windows and Devices head Pavan Davuluri made the claim at Microsoft's Windows and Surface event on October 7, where he also said Call of Duty support is coming in 2027. Apparently, no reason was given for the wait, and Microsoft didn't say which Call of Duty title they meant. That is an awkward gap, since Activision is a Microsoft-owned studio and the RTX Spark-equipped Surface Laptop Ultra starts at $2,599 with shipping set for October 16.

Anti-cheat is probably the holdup, although Microsoft hasn't confirmed that. RTX Spark uses an Arm-based CPU, so games run on Windows on Arm, and kernel-level anti-cheat drivers have to be rebuilt for it. Call of Duty relies on Activision's own Ricochet anti-cheat, which, as far as we know, only works on x86 systems today. Davuluri did show Gears of War: E-Day running at 60 FPS on the Surface Laptop Ultra. However, the resolution and upscaling settings were not disclosed, so the figure says little about real performance. It also isn't clear how many of those "hundreds" of games are native Arm builds and how many run through emulation. NVIDIA released its RTX Spark toolkit for Windows-on-Arm game development in July, and EA, Embark, and Ubisoft committed titles such as Apex Legends, ARC Raiders, and Anno 117: Pax Romana at Gamescom.

ASUS today announced the global launch of the new ProArt P16 and P14 laptops, along with the compact ProArt GR1X mini PC, all powered by NVIDIA RTX Spark. Purpose-built for creators, AI developers and workflow builders, these systems boast high-capacity unified memory, a powerful NVIDIA Blackwell RTX GPU and an ultra-efficient NVIDIA Grace CPU. The NVIDIA CUDA ecosystem and an expanding ASUS-exclusive agent-and-application solution make sophisticated local AI easier to deploy, personalize and use. NVIDIA RTX Spark unites NVIDIA AI, RTX graphics, and unified memory in one slim, powerful Windows PC. Designed to run larger AI models locally—without cloud dependency—and move between creative work, development, and immersive gaming without missing a beat. Connect apps, tools, and workflows into one seamless experience. Private by default, RTX Spark brings NVIDIA's full-stack AI platform, ready for the AI workloads of today and whatever comes next. Delivered on the familiar, trusted Windows platform.

Together, Hermes Agent and ComfyUI deliver a compelling local-first, cloud-flexible AI experience. By bringing industry-validated workflows and agent-connected creative tools to users' own PCs, they enable generative AI creation and AI-assisted development, with the flexibility to integrate cloud services when needed.

MSI, a global leader in high-performance and AI computing, today announced that the Prestige N16 Flip AI+ is now available for pre-order through MSI-certified partners in select markets.

Prestige N16 Flip AI+ is powered by NVIDIA RTX Spark, uniting NVIDIA AI, RTX graphics, and unified memory in one powerful and efficient thin-and-light Windows PC. Designed to run larger AI models locally—without cloud dependency—and move between creative work, development, and immersive gaming without missing a beat. Connect apps, tools, and workflows into one seamless experience. Private by default. RTX Spark brings NVIDIA's full-stack AI platform, ready for the AI workloads of today and whatever comes next. Delivered on the familiar, trusted, and secure Windows platform.

Dell Technologies announces an expanded portfolio of Windows PCs and workstations built for the age of agentic AI. Together with NVIDIA and Microsoft, Dell delivers agentic AI across every stage of the creative and development journey, spanning a premium creator laptop, compact creator desktop and an AI workstation within the Windows environment.

NVIDIA RTX Spark comes to the XPS and Dell lineup for the first time, powering the new XPS 16 Creator Edition laptop and Dell Creator Edition Desktop. Paired with Windows, RTX Spark brings advanced AI, creative and gaming workloads together on a platform optimized for its performance. Dell Pro Precision with GB300 will be available on Windows, bringing always-on AI compute into the environment enterprise teams already depend on.

Following what appears to have been a series of unfortunate events that led to a roadside laptop find resulting in confirmation that Microsoft will be launching a 20-core NVIDIA RTX Spark Surface Laptop, we now appear to have confirmation that Microsoft will also be launching a Surface Laptop Ultra on the other end of the Spark spectrum. According to Windows Central, Microsoft will reveal the full RTX Spark Surface line-up on October 7 at a special event in San Francisco.

Alongside the 20-core variant, the Windows Central report claims that Microsoft will launch a Surface Laptop with NVIDIA's 18-core RTX Spark. It is also claimed that the 18-core SKU will start with 24 GB of unified memory, while the 24-core version will start with 32 GB of memory. There will reportedly be a performance demonstration that shows off how the new Arm SoC delivers the same level of performance on battery life as it does when plugged into the wall.

ASUS today announced a new 64 GB configuration of ASUS Ascent GX10, expanding the lineup alongside the existing 128 GB model. This compact AI supercomputer is designed to bring local agentic AI development within reach of more developers, researchers and data scientists. Based on the NVIDIA DGX Spark platform and powered by the full NVIDIA AI software stack, ASUS Ascent GX10 64 GB delivers the same petaflop-scale architecture found on ASUS Ascent GX10 128 GB in a memory configuration built for today's efficient open-source models—enough to build and run today's most capable 30-35B class models and autonomous agents. When workloads grow, two systems can be clustered with the NVIDIA Sync Cluster Assistant for 128 GB of pooled memory and around 1.7X the throughput.

Ubiquitous AI, engineered for more builders
Guided by its Ubiquitous AI. Incredible Possibilities. strategy, ASUS is working to put agentic AI within reach of every builder, empowering not only the early professional AI teams already running frontier-scale models locally, but the much larger early-majority audience of developers, researchers and AI-curious teams who are ready to start experimenting hands-on.

Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally.

Coming this month, NVIDIA DGX Spark will be available with 64 GB of unified memory from top manufacturer partners—Acer, ASUS, Dell, Gigabyte, HP and MSI—giving developers, researchers and AI enthusiasts a new configuration with DGX OS and the NVIDIA AI software stack ready to use from day one.

Microsoft's Advanced Shader Delivery (ASD), which provides pre-compiled shaders with the game itself, is finally becoming available on a range of platforms. The company confirmed that this feature will expand to NVIDIA's GeForce RTX graphics cards and the RTX Spark platform later this month. This means that game developers will be able to ship pre-compiled shaders to speed up game loading times and reduce any shader-induced stuttering during gameplay. When Microsoft unveiled a public preview of ASD, it reportedly supported various AMD RDNA generations, but now more platforms are receiving support.

Currently, ASD is claimed to work on AMD RDNA 1, RDNA 2, RDNA 3, RDNA 3.5, and RDNA 4 GPU generations, as well as on Qualcomm Snapdragon X2 Series with Adreno integrated graphics. Later this month, Microsoft plans to extend ASD to Intel Arc B-Series, which includes B570, B580, Intel Core Ultra Series 2, and Intel Core Ultra Series 3. This update will coincide with support for all NVIDIA GeForce RTX GPUs and the RTX Spark platform, ensuring that every RTX-based GeForce system benefits from the speedup.

ASUS has already shown off its upcoming ProArt 16 creator laptop powered by the NVIDIA RTX Spark N1X Arm SoC at IFA 2026, but there was no exact launch date attached to the new laptops when we published our hands-on coverage on the show floor. Now, thanks to a new Weibo post by the official ASUS account, it has been revealed that ASUS will launch the ProArt P16 H7607BA (or a similar variant) on October 8, 2026—at least in China. It's not clear if this will be a simultaneous international launch, but, even if it isn't, an international launch shouldn't be too far behind.

ASUS on Weibo (machine translation)Smooth local AI agent response, creative workflows no longer reliant on the cloud
World's first AI agent PC | ASUS ProArt 16
Equipped with NVIDIA RTX Spark N1X super chip
Reconstructing the boundaries of professional creation, local computing power accelerates the implementation of the entire workflow
Coming October 8th

NVIDIA has rolled out RTX Kit 2026.3 alongside version 2.0 of its RTX Mega Geometry SDK, giving game developers a fresh batch of neural rendering and path tracing tools. The headline feature is support for streaming continuous level-of-detail clusters for high-density meshes, shown off in a new textured glTF version of the Zorah demo. The rest of the RTX Kit update covers RTX Character Rendering 1.4, RTX Dynamic Illumination 3.1 with DLSS Ray Reconstruction integration, RTX Neural Shading 1.4, and RTX Texture Filtering 1.3, which adds Collaborative Texture Filtering.

RTX Neural Texture Compression 0.10 is still in beta, but it now supports the DirectX 12 Agility SDK preview with Linear Algebra, letting Tensor Cores accelerate neural texture decompression in DirectX shaders. It and RTX Texture Filtering 1.3 also gain Windows ARM64 support, which seems to be groundwork for the RTX Spark PCs NVIDIA says start shipping in October. NTC was already running on Windows on Arm back in August.