16 GB accelerator memory
Q4 GGUF · llama.cpp
The ~14.3 GB community Q4 leaves little room; use reduced context and verify the approved artifact.
Mistral AI
Text model
A software-engineering model built for codebases and coding agents.
Capabilities
The most useful reasons to choose this model, without making you read through its repository first.
Repository work
Code generation
Developer agents
For providers
The provider requirements live here, separate from the information you need to choose and use the model.
16 GB accelerator memory
Q4 GGUF · llama.cpp
The ~14.3 GB community Q4 leaves little room; use reduced context and verify the approved artifact.
24 GB accelerator memory
Q4 GGUF · llama.cpp / MLX
Mistral names a single RTX 4090 or 32 GB Mac as a supported local target.
Source and license
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.