Mistral · 24B · Desktop / import

Mistral Small 3.2 24B on a phone

2025 Mistral Small — rich writing and analysis. GPU or 48 GB+ Mac.

Parameters
24B
Typical Q4
~13 GB (Q4)
RAM to budget
~18 GB
Engines
GGUF

Get it running

Mistral-Small-3.2-24B-Instruct-2506. Q4 ~13 GB. Hugging Face: mistralai/Mistral-Small-3.2-24B-Instruct-2506.

Load in LM Studio or Ollama, then chat from the phone.

Get LM Mini and load a model that actually fits — on-device, or via Connect to a PC.

Phones that can run it

  • None in this guide — use a Mac or Connect.

Tight (close other apps)

  • None in this guide — use a Mac or Connect.