FitLLM

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

Install

Remote server: your requests and data go to fitllm.run. Claude Code: claude mcp add --transport http fitllm https://fitllm.run/api/mcp · Claude app: Settings → Connectors → Add custom connector.

What it can do

The tools this server listed when we connected to it, in its own words.

• check_llm_fit — Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the
• what_fits_on_hardware — Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, big
• list_supported — List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only Huggin

KitScout test notes

Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.

Similar tools

• academy-guide 194,218 ★
  Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product
• claude-api 194,218 ★
  Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, c
• ccs-align 116,897 ★
  Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle ob
• mode-creator
• html-ppt-hermes-cyber-terminal