Bookmarks. Not a ranking we stole.
Where to grab a weight file, read a license, or stare at someone else's leaderboard. A score on those pages is not a Loaded Tokens verdict. We did not rerun their tests on a Tuesday night. If the question is the bill, start with the subscription and usage-limit checker.
If you want a short take on what is worth using, what to keep an eye on, and what you can skip for a specific tool, start at the open-source hub.
Check a bill
Model hubs
Hugging Face models
Weights, plus the model card that states the license. Read that card before the group chat does.
External page →Ollama library
Models packaged so you can pull them into a local Ollama server. Your fan will notice.
External page →Llama downloads
Meta's download page for Llama weights and the community license. The license is the homework.
External page →Leaderboards
LMSYS Chatbot Arena
A public preference board. Their rank is not a Loaded Tokens verdict, even if the screenshot looks official.
External page →Artificial Analysis
Independent model comparisons. Read their method before you paste a number into Slack.
External page →Open LLM Leaderboard
Hugging Face's board for open models. The score stays on their page. We did not adopt it.
External page →Learning
Local runtimes
llama.cpp
The local engine. The model you load still has its own license, like a roommate with a separate lease.
External page →vLLM docs
How to serve an open-weight model to software you run. The docs are the instruction manual, not a verdict.
External page →Whisper
OpenAI's speech model for local transcription. This download is not the hosted API.
External page →