fitllm

MCP serverAI & models

Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.

Serves today. ahel can serve it to every connected agent through your gateway link.

Serve it through your gateway

One link, every agent. Your own credentials, stored once.

Signals

GitHub stars
8
Forks
2
Last commit
Aug 2026