A new DIY build, the Redundant Array of Inexpensive Videocards (RAIV), pools seven used AMD Instinct MI50 32GB GPUs for about €3,530 to run large local AI models with redundancy, as described by Wirke…
Nvidia released PAIR (Personal AI Router), an open-source tool that distributes local AI inference requests across all compatible devices on a home network, reducing task completion times by half in a…
NVIDIA PAIR, a free open-source Personal AI Router in open beta for Windows, macOS, and Linux, pools idle GPUs across home networks to route inference requests to available machines, including Apple M…
Nvidia Corp. announced the Personal AI Router (PAIR) at IFA 2026 in Berlin, a beta tool that lets users cluster idle Macs and PCs in a home to run small language models and accelerate agentic AI workl…
NVIDIA has launched the beta of its Personal AI Router (PAIR), software that connects Windows PCs with RTX GPUs, DGX Spark systems, and Mac M4 or newer devices into a private home AI inference cluster…
NVIDIA launched PAIR (Personal AI Router) on September 3rd, an open-source beta that routes parallel AI inference requests across Windows, Linux, and macOS devices on a local network, targeting multi-…
Nvidia has introduced PAIR, a software layer that enables distributed AI inference across multiple GPUs on a local network, allowing users to pool consumer hardware instead of purchasing a single high…
Nvidia announced Personal AI Router (PAIR), a free, open-source tool that pools idle home PCs into a private AI compute cluster, at IFA 2026 in Berlin. PAIR supports GeForce RTX 20 Series and newer GP…
Nvidia launched Personal AI Router (PAIR), free open-source software that links multiple home computers over a local network to pool GPU power for AI inference without cloud use. Compatible with Ollam…
A user seeking advice on building a high-end AI inference system reports that their 8x R9700 setup underperforms compared to a single DGX Spark, citing 10 tokens per second on their system versus 21.6…
Pangolin, an open-source zero-trust network access suite, launched a new AI gateway that replaces API keys with WireGuard tunnels authenticated via existing identity providers such as Okta, Azure, and…
The State of Local AI Report, updated monthly, maps what AI models can run on user-owned hardware, finding that memory bandwidth dictates decode speed while compute dictates prefill speed, with an RTX…
FastH3, MiniMax's video-and-audio generation model, now runs on Apple Silicon via MLX and on NVIDIA's DGX Spark desktop, with two Sparks able to generate one clip together. The release also debuts the…
NVIDIA and MediaTek announced an expanded strategic collaboration, with NVIDIA investing $3.5 billion in MediaTek-issued convertible bonds. The partnership centers on MediaTek integrating NVIDIA's NVL…
NVIDIA and MediaTek announced an expanded collaboration to build AI computing platforms spanning AI infrastructure, local AI computing, and automotive, with NVIDIA investing $3.5 billion in convertibl…
A widely shared post from Jun Song claims the Mac Studio M5 Ultra with 512GB of unified memory draws about 350W at load, making it the most power-efficient local AI inference device, while a four-unit…
Apple's upcoming M5 Ultra, with 512GB memory and 1.2TB/s bandwidth, is projected to cost $15,000–17,000 when it ships in October, making local AI inference for models like DeepSeek V4 Pro, Kimi K3, an…
A developer tested the Qwen3.8-Flash-Next model on an NVIDIA DGX Spark (GB10, 128 GB unified memory) using llama.cpp with quantized KV cache, achieving 128K context and 414 tok/s prefill. They identif…
Perplexity launched Portable Computer, a local version of its agentic AI software that runs on-device to keep data off the cloud by default, available initially to Pro and Max subscribers on Nvidia's …
Perplexity launched Portable Computer on August 25, moving its Computer agent to run fully local on Nvidia's DGX Spark desktop, which costs $4,699, with zero per-token costs for local jobs. The initia…