🧩 Check which AI models your PC can run before you download them

[green_res]

Ranks every model by speed on your RAM and GPU, or on any machine you type in instead

AI models you run on your own PC are 2–40 GB files. Too big for your memory and it just won’t load — and you find that out after the download.

llmfit reads your RAM, cores and GPU first, then stamps every model:

Perfect · Good · Marginal · Too Tight

…with an estimated speed and the best compression your machine can hold. Free, MIT, no account.

brew install AlexsJones/llmfit/llmfit   # macOS / Linux
scoop install llmfit                    # Windows
uvx llmfit                              # no install

llmfit                                  # opens this ⤵

https://github.com/AlexsJones/llmfit

Everything below is one keypress inside that screen

	what it hands you
S	type any VRAM, RAM or core count — every row re-scores against a machine you don’t own yet
p	backwards: name a model, get the minimum VRAM, RAM and cores it needs
b	real speeds measured by people on your exact chip, plus 27 other cards under H
I	bench your own box against whatever you already have running
d D	pull it via Ollama, llama.cpp, LM Studio or MLX — history and deletion in D
f a P U C L R	filter by fit, installed, provider, use case, capability, license, runtime
v → c	line several models up side by side
A t	retune the speed maths · 10 themes

When numbers disagree: your own runs → people on identical hardware → public benchmark medians → the formula.

🧰 Shell, scripts, and a phone on the same wifi

llmfit quietly starts a dashboard on 0.0.0.0:8787 — open it from your phone. --no-dashboard kills it.

llmfit --memory=24G --ram=64G fit          # score a build you're pricing
llmfit plan "Qwen/Qwen3-4B" --context 8192 # hardware needed for one model
llmfit recommend --json --use-case coding  # top picks for scripts and agents
llmfit bench --all --share                 # measure, then PR the results back
llmfit serve --host 0.0.0.0 --port 8787    # REST API
llmfit info "<model>"                      # what a number assumed, and how to check it
llmfit doctor                              # hardware report when detection reads wrong

OLLAMA_HOST="http://192.168.1.100:11434" llmfit points it at a GPU box in another room.

MoE counted properly: Mixtral 8×7B looks like 46.7B parameters, but only ~12.9B fire per token — 23.9 GB drops to ~6.6 GB. And quantisation is walked Q8_0 → Q2_K instead of assumed, then retried at half context before anything is called Too Tight.

[Grace2077]

Handy idea – downloading a 20 GB model only to find it will not load is the classic local-AI time sink. A quick RAM and VRAM check up front would save a lot of people that frustration, especially on laptops where the GPU memory is shared. I would also love a rough speed estimate per model before downloading, since ‘it runs’ and ‘it runs usefully’ are two very different things on a smaller machine.

[Suraj_Pathak]

BRO, ARE U OMNIPOTENT?? How do u spawn EVERYWHERE?

[Adward_Dew]

very useful , thanks

[ai_daily_tools]

This is exactly the kind of check I wish I had done before my first local model download. I once grabbed a bigger model thinking my laptop could handle it, then spent ages waiting only to find it would not load properly. Checking RAM and GPU first feels obvious in hindsight, but it is easy to skip when you are excited about a new model. The speed estimate is the part I would actually use most, since a model that technically runs can still be painfully slow.