AMD's Ryzen AI Halo, a $3,999 desktop AI inference system with 128GB unified memory, launched July 10 at Micro Center, undercutting NVIDIA's DGX Spark by $700. Reviews confirm competitive performance …
A developer successfully runs the Qwen3.6-27B-FP8 model locally on an Nvidia DGX Spark, achieving reasoning, tool use, and multi-token prediction at 256K context, and uses it to ship real code for an …
AMD launched the Ryzen AI Halo Developer Platform, a $4,000 mini PC with 128GB of unified memory, targeting developers who need to run large local LLMs without cloud costs. The device uses a Ryzen AI …
AMD launched the Ryzen AI Halo workstation at nearly $4,000, offering 128 GB of unified memory for local AI model training and inference. The system is cheaper than Nvidia's DGX Spark but uses year-ol…
The FEX Emulator, a Valve-backed project for running x86/x86_64 software on ARM64 systems, released its FEX 2607 update with optimizations for yet-to-be-released 256-bit SVE2 ARM processors, improveme…
A developer created a daemon to reduce GPU temperatures on the NVIDIA DGX Spark by clock-locking via nvidia-smi -lgc. The daemon samples temperature every 30 seconds and adjusts clock ceilings, droppi…
Ahmad Osman, founder of Osmantic, argued at the AI Engineer World's Fair that local AI is rapidly catching up to proprietary frontier models, driven by shrinking gaps in open-source LLMs and improved …
DeepSeek launched DSpark, an open-source speculative decoding module that boosts AI inference speed by up to 400% on existing chips, potentially reducing demand for Nvidia's high-end accelerators. The…
Jaiveer Singh, a robotics software engineer at NVIDIA, leads the team behind Isaac ROS, an open-source framework that accelerates development of autonomous robots using CUDA-accelerated libraries and …
NVIDIA's DGX Spark, a $4,699 desktop AI supercomputer with 128GB unified memory, launched in 2025, offering one petaflop of FP4 performance. Benchmarks show it excels at prompt processing but lags in …
On May 16, 2026, llama.cpp merged Multi-Token Prediction (MTP) support, enabling 1.7x to 2.4x faster local inference for Qwen3.6 27B models with no accuracy loss or extra downloads. The MTP head is em…
NVIDIA's June 2026 DGX Spark update introduces automated four-node clustering via Cluster Assistant, enabling local inference of models up to 700B parameters. The update also delivers a 2.6x throughpu…
Nvidia has launched the DGX Spark, a $4,699 mini PC featuring a full Blackwell data center GPU, aiming to revolutionize local AI computing by bringing enterprise-grade hardware to individual users.…
Polar Signals storage engineer wrote a CUDA kernel to decompress FSST-encoded strings on GPUs, but initial performance was worse than CPU decompression. Using the company's GPU profiler with PC sampli…
GMKtec unveiled the redesigned EVO-X3 AI mini PC workstation, powered by AMD's Ryzen AI Max+ 395 processor with 128 GB of unified memory and an OCuLink port for eGPU expansion. The device, priced at $…
OpenCode, an open-source terminal-first coding agent, now supports self-hosted large language models via OpenAI-compatible APIs, enabling users to connect it to a vLLM server running NVIDIA's Nemotron…
Alibaba's Qwen3-80B and Qwen3-4B models were successfully co-located on a single NVIDIA DGX Spark using vLLM containers behind a LiteLLM proxy, but the 80B model's inability to emit tool calls in auto…
Local LLM inference splits into two phases—prompt processing (compute-bound) and generation (memory-bandwidth-bound)—explaining why hardware with identical token generation speeds can have vastly diff…
Nvidia announced the RTX Spark platform at Computex 2026, combining an Arm-based CPU, Blackwell RTX graphics, and unified memory to run AI models and agents locally on PCs. The platform targets develo…
Nvidia unveiled the RTX Spark Superchip at Computex 2026, an ARM-based processor developed with MediaTek that promises to revolutionize Windows PCs for AI developers, creators, and gamers. The chip, f…