Olivier Chafik
@ochafik
OpenSCAD & llama.cpp contributor, ex-Googler (views expressed = my own), he/him 🏳️🌈 @ochafik.bsky.social @[email protected]
Really slick integration! MCP all the (cool) things!
You really can just do things! Use *any* Hugging Face space as a MCP server along with your Local Models! 🔥 Here in we use Qwen 3 30B A3B with @ggml_org llama.cpp and @huggingface tiny agents to create images via FLUX powered by ZeroGPU ⚡ It's quite a bit crazy to see local…
Months of @ochafik's work finally paid off, we have MCP w/ llama.cpp 😁😁
biggest takeaway of all is Qwen 3 30B A3B is slept on and you should be playing around with MCP if you haven't already!
llama.cpp streaming support for tool calling & thoughts was just merged: please test & report any issues 😅 github.com/ggml-org/llama… #llamacpp
Gemma 3 VISION on llama.cpp server Still very early WIP, but it works 🔥
Docker is embracing the ggml/llama.cpp on-device future Who is going to be next?
WIP: streaming support for llama.cpp's tool calling + normalization of streamed <think> tags (for QwQ, DeepSeek R1 & Cohere Command R7B) Still strongly conforming to tool schemas (grammar-constrained). Testing / feedback welcome :-) github.com/ggml-org/llama…
Day-zero Gemma 3 support in llama.cpp 🤯 👉 4 model sizes: 1B, 4B, 12B, 27B 👉 Vision capability (except for 1B) with bi-direction attention 👉 Context size: 32k (1B) and 128k (4B, 12B, 27B) 👉 +140 languages support (except for 1B) 👉 Day-zero support on many frameworks 🚀
Loving this... hope OSS catches up quickly 🤗 Also, conforming to JSON schemas in a diffusion context is going to be an interesting challenge (schema / grammar compliance gradients anyone?)
Major AI breakthrough: Diffusion Large Language Models are here! They're 10x faster and 10x cheaper than traditional LLMs. Here's everything you need to know:
You're seeing a minor miracle: Phi-4 3.8B doing agentic tool calls. Doing that reliably, locally, even with 8B, has been a fools errand until @ochafik's opus of a patch series to llama.cpp (PR coming for phi-4)
llama.vscode (powered by Qwen Coder)
Make your Mac think faster 🧠🧠 Tomorrow I'll show you how to cancel your copilot subscription.
. @JLMelenchon au moment où le peuple syrien se libère de la dictature que vous avez toujours soutenu, la décence aurait voulu que vous vous taisiez. Vous avez choisi d'ajouter le mensonge à la longue liste de vos indignités sur le sujet. Alors, s'il ne fallait garder q'une…
Les Insoumis ont toujours apporté un soutien absolu et total à la lutte du peuple Syrien contre son dictateur. Et au peuple Kurde qui s'est battu sans relâche pour le socialisme, l'autogestion et le fédéralisme. Le reste, ce sont de pitoyables et habituels mensonges, calomnies.