# llmfit

> MIT CLI — which models fit your hardware

**Category:** AI Agents  
**Pricing:** open-source  
**URL:** https://github.com/AlexsJones/llmfit  
**GitHub:** https://github.com/AlexsJones/llmfit  
**Added:** 2026-09-15

---

## The Hook

llmfit answers one question: which of hundreds of models and providers actually fit the machine in front of you.

## What's Good

MIT (AlexsJones/llmfit). Rust/`cargo`/crates.io CLI. Catalog-aware hardware fit finder — VRAM, RAM, and provider options in one command instead of spreadsheet archaeology. Aimed at local/self-host planners before you pull a 70B that will not load.

## The Catch

Vs Ollama / llama.cpp / vLLM (runtimes): llmfit is the hardware fit finder, not the model runtime. Catalogs and VRAM heuristics drift; always verify against your real device and quantization. Does not download or serve models for you.

## Verdict

MIT hardware-fit CLI. Pick models that fit; run them elsewhere.