FitLLMv1.1.0remotelive
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
run.fitllm/fitllmsource
FitLLM
1 serverUnverified
Pick a model, quantization, KV cache and context — instantly see if a local LLM fits your NVIDIA RTX GPU or Apple Silicon Mac, and how much memory is left.
FitLLM (fitllm.run) publishes 1 MCP server on the Official MCP Registry, run remotely. That ranks it #925 of 17,135 companies by servers shipped, with its latest release on Sep 2, 2026.
- Website
- fitllm.run
- Rank
- #925
- Live
- 1 of 1
- First seen
- Oct 31, 2026
AI visibility
Does ChatGPT, Perplexity or Gemini name FitLLM when a buyer asks for what it does? Claim this page and we measure it every month, free.
1 MCP server published
Badge for your README
We check every server weekly: a remote that answers an MCP handshake, a package that resolves, or a repo that exists. Servers that fail for 30 days stop counting.
[](https://whobuildsagents.com/fitllm.run)
