https://upupabit.ai/ News about Matricxon and pAIring. en https://upupabit.ai/ upupabit-2026-10-13-the-upupabit-website-is-live Tue, 13 Oct 2026 09:00:00 GMT A new home for Matricxon and pAIring, with full documentation for both. https://upupabit.ai/docs/pairing/cluster/ upupabit-2026-10-11-cluster-mode-beta- Sun, 11 Oct 2026 09:00:00 GMT Several Matricxon nodes can now share models and chat caches, managed from a live node map in pAIring. https://upupabit.ai/docs/pairing/chat-and-channels/#tools upupabit-2026-10-04-tools-through-mcp Sun, 04 Oct 2026 09:00:00 GMT Connect MCP tool servers and let models look things up or take actions in chat. https://upupabit.ai/docs/matricxon/caching/ upupabit-2026-10-03-encrypted-saved-chat-caches Sat, 03 Oct 2026 09:00:00 GMT Matricxon keeps long chats ready on disk with AES-256-GCM, so returning to them is fast. https://upupabit.ai/docs/matricxon/kernels-and-gpu/ upupabit-2026-10-02-gpu-mode-experimental- Fri, 02 Oct 2026 09:00:00 GMT Matricxon can run on an NVIDIA GPU, with packed or unpacked weights. https://upupabit.ai/docs/matricxon/models/ upupabit-2026-10-01-qwen-3-5-support Thu, 01 Oct 2026 09:00:00 GMT Matricxon runs Qwen 3.5, including its hybrid layers and vision. https://upupabit.ai/docs/matricxon/models/ upupabit-2026-09-29-gemma-4-and-faster-moe Tue, 29 Sep 2026 09:00:00 GMT Matricxon runs Gemma 4, and mixture-of-experts models share one faster expert layer. https://upupabit.ai/docs/matricxon/models/ upupabit-2026-09-28-falcon-starcoder-2-and-mixtral Mon, 28 Sep 2026 09:00:00 GMT Three more model families join Matricxon, including its first mixture-of-experts model. https://upupabit.ai/docs/matricxon/models/#quantization-types upupabit-2026-09-28-the-full-i-quant-family Mon, 28 Sep 2026 09:00:00 GMT Matricxon reads 25 quantization types, now including the IQ1 to IQ4 types for very small models. https://upupabit.ai/pairing/ upupabit-2026-09-28-math-in-chat Mon, 28 Sep 2026 09:00:00 GMT pAIring shows math formulas in replies as clean, readable equations. https://upupabit.ai/docs/pairing/connectors/ upupabit-2026-09-27-connectors-for-cloud-gpus Sun, 27 Sep 2026 09:00:00 GMT pAIring can send chats to a RunPod Serverless endpoint when you need a bigger model. https://upupabit.ai/docs/matricxon/kernels-and-gpu/ upupabit-2026-09-23-native-c-kernels Wed, 23 Sep 2026 09:00:00 GMT Matricxon moved all dequantization to native C kernels, many times faster than before, with macOS support the same day. https://upupabit.ai/matricxon/ upupabit-2026-09-22-matricxon-is-open-source Tue, 22 Sep 2026 09:00:00 GMT The first public release of Matricxon, a readable GGUF runtime with Qwen 2 and Qwen 3 support. https://upupabit.ai/pairing/ upupabit-2026-09-22-pairing-is-open-source Tue, 22 Sep 2026 09:00:00 GMT pAIring 1.0, a private AI chat workspace for teams, is released under AGPL-3.0.