NVIDIA ACE supports Qwen3-8B for dynamic NPCs, Magpie Flow gets multilingual support, and a new Unreal Engine 5 tech demo is out

🔥 The AMD #MI355x isn’t just another GPU — it’s a performance powerhouse... Validated by third-party experts at Hot Aisle, this is delivering real PFLOPS. 🚀 Running AI video workloads on Wan2.2, we’re seeing sustained performance with peak power around 8000W — and it’s staying cool thanks to direct liquid cooling. 🧊⚡ This is what next-gen compute looks like. Not theoretical. Not simulated. Live. Fast. Real. #AMD #MI355x #AICompute #HotAisle #Wan2 #DataCenter #AMDBrandAmbassador

Using NVIDIA’s Cosmos-Transfer1-DiffusionRenderer to relight live-action footage with HDRI. It produces an impressive ALBEDO, with shadows accurately cast from the HDRI light source. I customized it to process HDRI sequences, allowing calculation with arbitrary motion and position. However, the resolution is limited to 1280x720 and only up to 57 frames can be processed at once. I used an official overlapping code release to fake longer sequences. The image quality still degrades, so it’s not suitable for direct use—but I tried blending it slightly into the opening of the first cut this time.

The HL15 Beast is Here — Built with the Homelab Community 💥 We asked the homelab community what they wanted in the next evolution of the HL15, and you spoke. The result? The HL15 Beast — a 5U powerhouse designed to handle gaming, AI, video editing, and self-hosting with unmatched speed and cooling. With 15 direct-wired 3.5" drive bays and 8 dedicated 2.5" SATA SSD bays, this server makes lightning-fast storage and caching effortless. Premium Noctua fans and integrated dust filters keep everything running cool, while a rugged, North American-made steel chassis ensures your system is built to last. Now we want to hear from you: if you had the HL15 Beast in your lab, what would you power first — an AI project, a gaming rig, or a massive homelab setup? Comment below and let’s see how the community would push this beast to the limit! Discover the HL15 Beast today: https://loom.ly/Tb8AQRA #HL15Beast #HomelabCommunity #SelfHosting #HighPerformanceServer #EATXServer #NAS #TechEnthusiast #AIReady #VideoEditingRig #MadeInNorthAmerica #45Drives

NVIDIA sent us a 5090 so we can demo Qwen3-VL 4B & 8B GGUF. You can now run it in our desktop UI, Hyperlink, powered by NexaML Engine — the first and only framework that supports Qwen3-VL GGUF right now. We tried the same demo examples from the Qwen2.5-32B blog — the new Qwen3-VL 4B & 8B are insane. Benchmarks on RTX 5090 (Q4): Qwen3VL-8B → 187 tok/s, ~8GB VRAM Qwen3VL-4B → 267 tok/s, ~6GB VRAM Thanks NVIDIA and Qwen — local multimodal just went beast mode. More optimizations are coming. Run it yourself in Hyperlink — one-click install, fully local, beautiful UI. What interesting Qwen3VL use cases will you discover? Download link below.

News drop 📣 👤 NVIDIA ACE now supports Qwen3-8B for on-device deployment of real-time, dynamic NPCs. Available now as an SDK plugin. 💬 Magpie Flow text-to-speech received multilingual support for testing within end-to-end character pipelines. 🖼️ We just released a new tech demo for the RTX Branch of Unreal Engine 5 showing off RTX Mega Geometry, ReSTIR PT, and DLSS 4.

News drop 📣 👤 NVIDIA ACE now supports Qwen3-8B for on-device deployment of real-time, dynamic NPCs. Available now as an SDK plugin. 💬 Magpie Flow text-to-speech received multilingual support for testing within end-to-end character pipelines. 🖼️ We just released a new tech demo for the RTX Branch of Unreal Engine 5 showing off RTX Mega Geometry, ReSTIR PT, and DLSS 4.

News drop 📣 👤 NVIDIA ACE now supports Qwen3-8B for on-device deployment of real-time, dynamic NPCs. Available now as an SDK plugin. 💬 Magpie Flow text-to-speech received multilingual support for testing within end-to-end character pipelines. 🖼️ We just released a new tech demo for the RTX Branch of Unreal Engine 5 showing off RTX Mega Geometry, ReSTIR PT, and DLSS 4.

News drop 📣 👤 NVIDIA ACE now supports Qwen3-8B for on-device deployment of real-time, dynamic NPCs. Available now as an SDK plugin. 💬 Magpie Flow text-to-speech received multilingual support for testing within end-to-end character pipelines. 🖼️ We just released a new tech demo for the RTX Branch of Unreal Engine 5 showing off RTX Mega Geometry, ReSTIR PT, and DLSS 4.

News drop 📣 👤 NVIDIA ACE now supports Qwen3-8B for on-device deployment of real-time, dynamic NPCs. Available now as an SDK plugin. 💬 Magpie Flow text-to-speech received multilingual support for testing within end-to-end character pipelines. 🖼️ We just released a new tech demo for the RTX Branch of Unreal Engine 5 showing off RTX Mega Geometry, ReSTIR PT, and DLSS 4.