MCP.so
Sign In

FitLLM

@click6067-ship-it

RepositoryHomepage

About FitLLM

Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Remote server: https://fitllm.run/api/mcp

#llm#vram#gpu#hardware#apple-silicon#quantization#multi-gpu#calculator

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "fitllm-engine": {
      "command": "npx",
      "args": [
        "fitllm",
        "GLM-4.7-Flash",
        "--gpu",
        "4090",
        "#",
        "✓",
        "FITS",
        "—",
        "21.9/24",
        "GB,",
        "free",
        "2.1",
        "GB"
      ]
    }
  }
}

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Fitllm Engine?

Will this LLM fit your GPU or Mac? npx fitllm — accurate memory math for MLA/sliding-window/hybrid/MoE architectures that naive VRAM calculators get wrong by up to 18x. Single file, zero deps, conformance-vector tested. MIT.

How to use Fitllm Engine?

The README includes setup instructions such as npx fitllm "GLM-4.7-Flash" --gpu 4090 # ✓ FITS — 21.9/24 GB, free 2.1 GB.

Key features of Fitllm Engine

  • Architecture values checked against official HuggingFace config.json
  • Calibration: Qwen 3.6 35B-A3B @128K, 8-bit ≈ 54 GB (matches real local runs)
  • MLA per-token cost: GLM-4.7-Flash = (512 + 64) × 2 B × 47 layers = 54,144 B/token — pinned by conformance vectors
  • Claude Code: claude mcp add --transport http fitllm https://fitllm.run/api/mcp
  • Cursor / Windsurf: add to mcp.json → { "mcpServers": { "fitllm": { "url": "https://fitllm.run/api/mcp" } } }

Use cases of Fitllm Engine

  • Connect an MCP-compatible client to this repository's service.
  • Review the README-backed setup before enabling it in production.

FAQ from Fitllm Engine

Where is the source code for Fitllm Engine?

The source code is linked from the repository URL on this page.

Does Fitllm Engine include a standard MCP config?

If the README contains a parseable MCP configuration block, it is shown in the Config tab.

Frequently asked questions

Where is the source code for Fitllm Engine?

The source code is linked from the repository URL on this page.

Does Fitllm Engine include a standard MCP config?

If the README contains a parseable MCP configuration block, it is shown in the Config tab.

Comments

Basic information

Category

Developer Tools

License

MIT

Author

click6067-ship-it

Submitted by

Yo

More Developer Tools MCP servers

Rams

HSLA0001 Inc.

Design review for UI code, inside your agent. One tool (review_files): up to 20 files in, a scored review out — 0–100, issues with severity and file:line, a concrete fix for each. 258 versioned rules across accessibility

extentos

Asger mølgaard

Extentos is a multi-vendor development platform for adding smart-glasses capabilities to existing iOS and Android apps. The simplest analogy is Stripe for smart glasses:

PuzzleTide Puzzle Generator

Caravaca-Labs

Word search generator, crossword generator, and sudoku generator + solver as a local-first MCP server. 15 deterministic tools: printable PDF puzzle worksheets, themed word banks, and verifiable LLM evals. From the makers

TaskerArmy Agent

TaskerArmy

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.

FastAPI-MCP

tadata-org

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

11.9K