Loading activity…
@ggerganov
24th at the Electrica puzzle challenge | building https://github.com/ggml-org | engineer @huggingface
AI
A user shares a `llama serve` command specifying Qwen3.8-Flash-Next-GGUF:IQ4_NL, `draft-mtp` and lazy mode.
AI
Microsoft said GitHub Copilot will soon route some tasks to local models on Windows and others to cloud-scale models. The company tied that plan to its broader “hybrid intelligence” push, while separately saying MXC sandboxing is now generally available on Windows 11.
YouTubeAI
The user says llama.cpp supports native mxfp4 weights out of the box; another says ggml RPC distributes inference across devices.
AI
The release announcement touts Qwen3.8-Flash-Next support, major Metal performance gains and a new `llama_batch_ext` API.
Technology
ggml-org says the endpoint scores supplied options and returns probabilities in a single forward pass instead of generating text.
AI
A post on X shares Bloomberg details on a potential Nvidia purchase of the AI company Hugging Face.
AI
Georgi Gerganov shared the update for the Llama macOS application.
