Meta releases new on-device optimized open source model
Summary
Meta announces a new open-source model optimized for on-device deployment, aiming to bring efficient AI inference to edge devices.
Similar Articles
With new open models, Meta pitches another reboot of its struggling AI strategy
Meta is pitching a reboot of its AI strategy with new open models, arguing for personalized, decentralized AI instead of a single superintelligence. The company lags behind OpenAI and Anthropic, positioning itself as a US alternative to Chinese open-model labs like Alibaba and DeepSeek.
Meta's new open-weight model targets local agentic AI
Meta announces a new open-weight model aimed at local agentic AI, with Mark Zuckerberg sharing his essay on Meta's AI philosophy.
Meta has confirmed that it will release an open source model in the future
Meta confirmed plans to release an open source AI model in the future, signaling continued commitment to open-source AI development.
@cpaik: Open-source Many model Inference on device
An open-source tool for running multiple AI model inferences on local devices, enhancing on-device AI deployment efficiency.
Edge0/Edge0-35B-A3B-preview
Edge0-35B-A3B-preview is a sparse MoE model that enables efficient AI inference on mobile devices by using streaming expert offloading and quantization, achieving 15 tok/s with under 3 GiB of memory.