AI Briefing#local-ai
The latest AI and developer news about #local-ai, with the original source and a short summary.
The latest AI and developer news about #local-ai, with the original source and a short summary.
Perplexity has released the Windows version of 'Portable Computer', a local AI agent that supports NVIDIA RTX GPUs.
A study reveals that the Intelligence per Watt (IPW) efficiency of local LLMs has improved 5.3x over three years, demonstrating the potential to offload central infrastructure demand for a significant subset of queries.
NVIDIA has released 'PAIR', an open-source tool that connects multiple local computers to distribute AI inference requests.
The open-source local TTS 'LoudKit', supporting voice cloning and 10 languages, has been released.
NVIDIA has released the beta version of 'PAIR', a software that connects various devices such as RTX, DGX, and Mac into a single local AI cluster.
Nvidia unveils laptops and mini PCs equipped with the RTX Spark superchip, targeting the local AI execution market.
NVIDIA expanded its local AI ecosystem at IFA 2026 by unveiling local inference optimization tools and RTX Spark PCs.
The open-source desktop research tool 'Open Science Desktop' has been released, recording the provenance and execution environment of AI agent outputs locally.
The local audio AI framework audio.cpp 0.7 has been released, supporting 62 model families and an Arena UI for comparison.
Lemonade, a local AI development tool, released a summer update adding support for 15 engines and semantic routing features.
Apple unveiled the 2nm-based M6 and the quad-die M5 Ultra, significantly enhancing local AI performance.
Perplexity has launched 'Portable Computer', an AI agent that runs locally without cloud costs, in partnership with Nvidia.
Microsoft has confirmed a structure that forcibly inserts GUID watermarks via remote servers even when generating AI images locally.
Qwen3.6-35B is faster in speed but has longer inference times, resulting in slower final response times.
FreeToken provides an edge-native serving system that efficiently runs large MoE models by leveraging the heterogeneous resources of personal devices.
Unsloth has launched the Desktop beta, integrating local model execution, training, and agent capabilities.
NVIDIA is partnering with the local AI community to expand the ecosystem of open models and agents.
Muse Glimmer has been released as a 30B open-weight agent model capable of running on 24GB-class memory.
Meta has released Muse Glimmer, a 30B multimodal model for local agents, under the Apache 2.0 license.
Bento has released a single-HTML presentation format with built-in editing and presentation capabilities.
The llama.cpp team has unveiled a Mac app and simplified model serving feature.
LocalAI has revealed the performance and cost of its own C/C++ inference engines, which reduce Python dependencies.
WASTE ran the 2.78 trillion-parameter Kimi K3 on 64GB of memory.
ODS, an open-source stack that installs various AI tools like Ollama, Open WebUI, and n8n all at once, has been released.