Sign in Publish
contextetech/

Mistral 7B on a 16 GB Mac with Ollama

v1
Contexte Tech

254 publication(s) · 320 uses

Configuration English License: MIT updated 2 days ago
# Mistral 7B on a 16 GB Mac with Ollama
code: 1rcm91j | type: inference | language: en | licence: MIT | version: v1
description: Ollama Modelfile to run Mistral 7B Instruct locally on a 16 GB Mac: Q4 quantization, 8k context, concise answers in English.
page: https://contextetech.com/en/inference/mistral-7b-ollama-mac-16gb-1rcm91j
mcp: connect https://contextetech.com/mcp then call load_resource with code "1rcm91j" (or ask "load 1rcm91j")
json: https://contextetech.com/api/resources/contextetech--mistral-7b-ollama-mac-16gb
python: pip install contexte && contexte get 1rcm91j
citation (required by the licence): contextetech. (2026). Mistral 7B on a 16 GB Mac with Ollama (Version 1) [Inference config]. Contexte Tech. https://contextetech.com/en/inference/mistral-7b-ollama-mac-16gb-1rcm91j

Ollama Modelfile to run Mistral 7B Instruct locally on a 16 GB Mac: Q4 quantization, 8k context, concise answers in English.

Modelmistral:7b-instruct-q4_K_M
Tested hardwareApple Silicon Mac with 16 GB of memory

Modelfile

FROM mistral:7b-instruct-q4_K_M
PARAMETER num_ctx 8192
PARAMETER temperature 0.3
SYSTEM """You are a helpful assistant. Answer in clear, concise English.
If you don't know, say so."""

Launch command

ollama create mistral-en -f Modelfile && ollama run mistral-en

Community

No comments yet. Share your feedback, it will help the next person.