Mesh LLM: Distributed AI for pooling local compute

alex_verem · x · 2026-08-25

Mesh LLM is an open-source project that pools GPUs and memory across multiple machines (desktops, laptops, old rigs) to run a single AI model. Models too large for one machine are split across stages in the mesh. It exposes an OpenAI-compatible API, supports CUDA/AMD/Vulkan/Apple Silicon, and works with major open families like Qwen, Llama, DeepSeek, and GLM.

Original post →

More from Infra

Infra channel →