Models · 25 tracked

Pick a model by what you have and what you want it for.

Every model here can be downloaded and run on your own hardware. The number that matters most is the memory it needs, so the list is grouped by it.

Fast models1 of 25

15B or fewer parameters used per token — including mixture-of-experts models. Fewest first. Show all models

Filters1
Reset

A 32 GB graphics card

22–30 GB

Or a Mac with 48 GB of memory.

  • Efficient model for everyday chat.Mistral AI · Runs well on many reference systems
    ~30 GB estimateto runPermissive

Parameters, context length, capability profiles and side-by-side comparison are in the Technical view.