Skip to content
AI Stack Nest

Open-source AI and Llama hub

Everything to pick, install and run open models on your own computer.

Open models

An open model is one whose weights you can download and run yourself, on a laptop, a desktop or a rented GPU, without sending your text to a hosted service. This table lists each model with its size, license and the memory it needs. Read the license column before you build anything commercial, because "open" does not always mean "free to use for business".

Model directory
ModelMakerSizeLicenseContextBest forCommercialMemory (4-bit)
Gemma 2 9B Google9BGemma Terms of Use8KCompact general chat for machines with 8 to 16 GB of memoryAllowed under the Gemma terms; read them6.9 GB
Llama 3.1 70B Meta70BLlama 3.1 Community License128KWorkstations or servers with a lot of memoryAllowed under the Meta license terms; read them43.5 GB
Llama 3.1 8B Meta8BLlama 3.1 Community License128KGeneral chat on a laptop with 8 GB or more of memoryAllowed under the Meta license terms; read them6.3 GB
Mistral 7B Instruct v0.3 Mistral AI7BApache 2.032KSmall local assistants, with a permissive licenseYes5.7 GB
Qwen2.5 7B Instruct Alibaba Cloud7.6BApache 2.032K (128K with YaRN)Multilingual chat and coding on a laptopYes (Apache 2.0 for this size)6.1 GB