run.fitllm/fitllmai

FitLLM

Verified · today

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

Install

claude mcp add --transport http fitllm https://fitllm.run/api/mcp

Our take

Calculates whether a given model will fit on a GPU, multi-GPU setup, or Mac, with emphasis on VRAM and KV-cache sizing. It is for developers and operators planning local inference capacity before spending time on downloads or deployments. The scope is narrow but clear, and the read-only design reduces risk; maturity appears early based on the small public footprint.

reviewed by hand · 2026-07-10

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
7
last commit
today
archived
no
license
MIT
in registry since
2026-07-09

github.com/click6067-ship-it/fitllm-engine

More in ai

browse all →
claude-flowai

claude-flow

Verified · 2 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed63k starschecked 2 days ago

tldrawai

tldraw

Verified · 3 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed49k starschecked 3 days ago

strataai

strata

Verified · 4 days ago

MCP server for progressive tool usage at any scale (see https://klavis.ai)

hand-reviewed5.8k starschecked 4 days ago

mcp-server-chartai

mcp-server-chart

Verified · 4 days ago

A Model Context Protocol server for generating charts using AntV.

hand-reviewed4.2k stars36k dl/wkchecked 4 days ago

semai

sem

Verified · today

Entity-level code intelligence: semantic diff, impact analysis, blame, and context for AI agents

hand-reviewed3.1k stars3.7k dl/wkchecked today

ros-mcp-serverai

ros-mcp-server

Verified · yesterday

Connect AI models like Claude & ChatGPT with ROS robots using MCP

hand-reviewed1.3k starschecked yesterday