About FitMyLLM

What is this?

FitMyLLM is a free tool that helps you find the best Large Language Model for your specific hardware. Instead of guessing whether a model will run on your GPU, you get concrete estimates based on real specifications.

Why we built it

Running LLMs locally is becoming increasingly popular, but choosing the right model is confusing. You need to consider VRAM, memory bandwidth, quantization levels, and how these affect both quality and speed. Most people either pick a model that is too big (and runs painfully slow) or too small (missing out on better quality).

We wanted a tool that gives honest, data-driven recommendations—not marketing hype.

How it works

We combine three data sources:

• Hardware specs database — 121 GPUs and 35+ CPUs with detailed specifications (VRAM, bandwidth, compute performance)
• Model benchmarks — Data from the Open LLM Leaderboard on HuggingFace, including IFEval, BBH, MATH, GPQA, and more
• Performance formulas — Physics-based calculations for token generation speed, VRAM usage, and inference modes

For the full technical details, see our Methodology page.

Limitations

Our estimates are approximations based on theoretical calculations. Real-world performance depends on many factors: your specific system configuration, the inference engine you use (llama.cpp, Ollama, vLLM), background processes, and more.

We are constantly improving our models. If you find significant discrepancies between our estimates and your real-world results, please let us know.

Why private AI is the future

Today, every question you ask a cloud AI is stored on someone else's server. Your conversations, your code, your medical questions, your business ideas — they become training data, revenue sources, and potential breach targets. This model is not sustainable, and it's not ethical.

The alternative already exists. Open-source models running on your own hardware deliver GPT-4-level quality for most tasks — with zero data leaving your machine. No terms of service granting companies rights over your inputs. No API keys that can be revoked. No monthly fees that keep rising.

Private AI means:

• True data sovereignty — Your conversations are not stored, analyzed, or used to train anyone else's model. Ever. What happens on your machine stays on your machine.
• Independence from corporations — No company can change the rules, raise prices, censor outputs, or shut down your access. You own the model file like you own a book.
• AI for everyone, not just those who can pay — A one-time GPU investment gives you unlimited AI access. No $20/month subscriptions, no per-token billing, no rate limits at 3am when you need it most.
• Works everywhere, always — On a plane, in a restricted network, in a country where certain AI services are blocked. Local AI has no borders and no downtime.

FitMyLLM exists because we believe this transition should be easy, not just possible. We don't collect your data, we don't track your choices, and we don't promote any vendor. We just help you find the best model for hardware you already own.

By the numbers

Support the project

FitMyLLM is free to use and always will be. If you find it useful, you can support development by buying me a coffee.

Independence & Transparency

FitMyLLM is an independent project. We are not sponsored by and have no business relationship with Ollama, HuggingFace, NVIDIA, AMD, Apple, or any model provider. Our recommendations are based purely on technical data and benchmarks.

Some hardware links on this site are affiliate links — if you purchase through them, we may earn a small commission at no extra cost to you. This never influences our recommendations: the same data-driven algorithm ranks hardware regardless of whether an affiliate link exists for it.