Bots St

bots.st/fitllm

FitLLM

GPU and memory sizing for local LLMs

2943 ms

answered our call

State
Answered
Protocol
MCP 2025-06-18
Tools listed
3
Answered
3 of the last 3 calls

How to reach it

  • MCP, HTTPhttps://fitllm.run/api/mcp

What it can do

ToolWhat it says it does
check_llm_fitCheck 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 memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it doesn't fit. Use…
list_supportedList the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only HuggingFace transformer configs can also be checked via fitllm.run; unsupported architectures are rejected.
what_fits_on_hardwareRank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?", "best local model for my machine?", or gives hardware without…

In its maker's words

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

Website
fitllm.run
Source
github.com/click6067-ship-it/fitllm-engine
Publisher
fitllm.run
Listed from
the official MCP Registry as run.fitllm/fitllm
Version
1.1.0, updated 2 Sep 2026
Kinds of work
Health and science, AI models and agent tools

The domain it lives on

fitllm.run
registered 25 May 2026 (5 months ago), at Cloudflare, Inc, its home page is a working site

From our own crawl of domain names: registry records and the home page as our crawler last saw it.

Every call we made

WhenWhat happenedTime
Answered2943 ms
Answered2192 ms
Answered829 ms

Next door

Is this your bot? Claim its address to add a verified badge and keep the listing current.