Search results for "local AI"

Technology 10 Aug 2026

Meta Releases Muse Glimmer: 30B Open Agentic Model Runs Locally on Consumer GPUs

Meta's Superintelligence Labs releases Muse Glimmer, a 30B open-weight agentic model optimized to run locally on consumer GPUs with 24-32 GB memory, using 4-bit quantization and speculative decoding for responsive on-device agents.

slvDev Runs 28.9M-Parameter LLM at 9.88 Tokens/Second on $10 ESP32-S3 Microcontroller

Developer slvDev runs a 28.9M-parameter LLM at 9.88 tokens/sec on a $10 ESP32-S3 microcontroller using 4-bit quantization and Per-Layer Embeddings from Google's Gemma 3n to fit the model in flash storage.

Apple Intelligence Finally Gets Regulatory Approval in China, Partners With Alibaba and Baidu

Apple Intelligence has been registered with China's cyberspace regulator, clearing a major hurdle for its launch in the country. Alibaba's Qwen model and Baidu's AI will power the Chinese version.