Run Magistral Small locally: hardware requirements
Magistral Small by Mistral installs on a paired computer through idapt's local engine. RAM decides whether a build fits; a GPU only changes speed. Local runs are not billed.
- Download
- 13 GB
- RAM needed
- 20 GB
- Builds
- 1
Will it run on your machine?
Enter your system RAM to get verdicts. RAM decides whether a build fits; a GPU only changes speed.
Every build
| Build | Quantization | Download | RAM needed |
|---|---|---|---|
| 24bDefault | full precision | 13 GB | 20 GB |
RAM figures are working-set recommendations: when GPU memory is short, the runtime spills to CPU and system memory instead of failing.
Install it
Pair a computer with idapt and install Magistral Small from the model page: the local engine bootstraps itself, pulls the build you pick, and streams progress. Or pull it directly:
ollama pull magistral:24bFrequently asked
How much RAM do I need to run Magistral Small locally?
The smallest Magistral Small build runs with about 20 GB of system RAM; the largest needs 20 GB. RAM is the binding requirement: when GPU memory is short, the runtime spills to CPU and system memory instead of failing.
Which quantization of Magistral Small should I pick?
Start with the default 24b build: a 13 GB download that wants about 20 GB of RAM. Smaller quantizations shrink the download and memory needs at some cost in output quality; larger ones do the reverse.
Do I need a GPU to run Magistral Small?
No. A GPU with enough VRAM makes generation faster, but Magistral Small runs on CPU and system RAM alone. Whether a build fits is decided by RAM; the GPU only changes speed.
How big is the Magistral Small download?
About 13 GB for the single available build.
Can idapt install Magistral Small for me?
Yes. Pair a computer with idapt and install Magistral Small from this page: the local engine bootstraps itself, pulls the build you pick (ollama pull magistral), and streams download progress. Local runs are not billed.
Part of the Magistral Small model page · Check every local model against your hardware