Mistral · 7B · Desktop / import

Mistral 7B Instruct on a phone

Classic open model — clear writing and solid general knowledge on Mac or GPU.

Parameters
7B
Typical Q4
~4.1 GB (Q4)
RAM to budget
~6.5 GB
Engines
GGUF

Get it running

Mistral-7B-Instruct v0.3; ubiquitous GGUF quants. Hugging Face: mistralai/Mistral-7B-Instruct-v0.3.

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

Tight (close other apps)