Skip to main content
Magnitude detects your hardware, recommends local models for your machine, and lets you browse other compatible configurations in the catalog. Open /settings to manage models, browse the catalog, or inspect your hardware.

​
Hardware detection and profiling

Magnitude detects your processor, memory, system architecture, and acceleration such as Metal or CUDA. It then runs short local inference tests to estimate which model configurations will fit and how fast they should run without downloading complete model weights. Magnitude reuses the profile until your hardware or inference engine changes. Open /settings → Hardware to inspect the results.

​
Recommendations

Magnitude combines the hardware profile with its curated model data to recommend a small set of configurations for your machine. Each recommendation is a specific model, quantization, and context size.
  • Balanced offers the best overall mix of coding ability, speed, and memory use.
  • Best Quality prioritizes coding ability or higher model fidelity.
  • Fastest prioritizes response speed.
  • Lightweight uses less memory and disk space.
Recommendations consider coding ability, estimated speed, context, runtime memory, download size, and how much quality is retained by the quantization. They can differ between computers even when both machines have enough memory for the same model. Speed is shown as an estimate at the displayed context size, such as ~36 tok/s at 200K ctx. Actual performance varies with prompt length, other work running on the computer, and the exact model revision.

​
Model catalog

Recommendations are a short list selected for your machine. The catalog contains the complete curated set of local model configurations Magnitude can evaluate for it. Open /settings, then select catalog to compare model details including recommendation, memory, coding intelligence, quantization quality, speed, context, and license information. You can download another model at any time or select one that is already installed. Magnitude-managed models are stored in ~/.magnitude/models. Magnitude also checks the Hugging Face Hub cache for compatible GGUF models, respecting HF_HUB_CACHE, HUGGINGFACE_HUB_CACHE, HF_HOME, and XDG_CACHE_HOME before falling back to ~/.cache/huggingface/hub.