284B inference just hit 30 tok/s over open WAN iroh v1.4.1 shipped this week. Mesh-LLM v0.78.1 patched chunked-request admission. 9 open-source GitHub repos that turn idle GPUs into one P2P inference mesh: 32,304 combined stars. All permissive. 6 pushed in the last 8 days, stars as of Oct 22. JOIN THE MESH 01. iroh ★12.8k: -> QUIC transport, NAT hole-punching 02. rust-libp2p ★5.6k: -> peer discovery and relay routing 03. kalavai-client ★222: -> pool spare GPU capacity SPLIT THE MODEL 04. shard ★465: -> stream layer blocks across WAN 30.15 tok/s on 284B, six RTX 5090s, shard README 05. distributed-llama ★3.1k: -> split weights across home devices 06. prima.cpp ★113: -> 70B on laptops and phones 674 ms vs 10,120 ms, 15x over llama.cpp, prima.cpp README ROUTE REQUESTS 07. mesh-llm ★3.5k: -> one OpenAI API over pooled GPUs 08. pooled ★604: -> P2P inference in the browser 09. gpustack ★5.9k: -> schedule models across GPU nodes the mesh: peer → discover → relay → pool → shard → route → schedule → endpoint curl -fsSL | bash Not a bigger GPU. A mesh of whatever you already own. Most nodes alpha. Prompts travel open wire unless the mesh is private ⭣