A developer building a home AI server from e-waste GPUs details the process of optimizing multi-GPU performance for running large language models, focusing on llama.cpp settings and existing technique…
Ornith-1.0, a June 2026 open-weight coding model, claims to learn by building its own harness during training, and its 9B model matches or beats Gemma4-31B on SWE-Bench Verified and Terminal-Bench 2.1…
Meta Superintelligence Labs released Muse Glimmer on August 10, a 30B-parameter open-weight model under Apache 2.0, designed for local agentic workflows and tool calling. The model, available on Huggi…
Meta has open-sourced Muse Glimmer, a 30-billion-parameter agentic AI model that runs on consumer hardware, in a move aimed at challenging closed AI labs and Chinese open-weight competitors. The model…
Meta released Muse Glimmer 30B on August 10, 2026, an open-weight model under Apache 2.0 designed for local AI agents, fitting on a single consumer GPU. It reached #1 on Hacker News with over 1,000 po…
Meta Superintelligence Labs released Muse Glimmer, a 30-billion-parameter agentic model under Apache 2.0 that runs on a single 24GB consumer GPU, with benchmark wins in agentic tasks (MCP Atlas 75.5) …
Meta's Superintelligence Labs released Muse Glimmer, a 30B-parameter local AI model, which outperforms Google's Gemma4-31B and Alibaba's Qwen3.6-27B on most benchmarks, including a 75.5 score on MCP A…