Mistral 7B on a 16 GB Mac with Ollama
# 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.
| Model | mistral:7b-instruct-q4_K_M |
|---|---|
| Tested hardware | Apple 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
- Identifier
- contextetech--mistral-7b-ollama-mac-16gb
- File
- Modelfile
- Format
- MODELFILE
- Size
- 184 bytes
- Encoding
- UTF-8
- Estimated tokens
- ≈ 51
- Commercial use
- Allowed
- Personal data
- None
- Version
- 1.0
- Published on
- October 2, 2026 at 9:54 PM
- Updated on
- October 16, 2026 at 11:19 PM
- Storage
- in database
Statistics
Likes : 0 · Comments : 0
Click a counter to show or hide it, hover the chart for details. One view per visitor per day, bots excluded; counting started on 30 September 2026.
Estimated cost
- Input tokens per call
- ≈ 191
| Model | Per call | Per month |
|---|---|---|
| GPT-6 Luna · OpenAIbest price | €0.00002 | €0.02 |
| DeepSeek Flash · DeepSeek | €0.00005 | €0.05 |
| Mistral Large · Mistral AI | €0.00008 | €0.08 |
| DeepSeek V4 Pro · DeepSeek | €0.00022 | €0.22 |
| GPT-6 Sol · OpenAI | €0.00034 | €0.34 |
| Claude Sonnet 5.5 · Anthropic | €0.00034 | €0.34 |
| Claude Opus 5.5 · Anthropic | €0.00067 | €0.67 |
| Self-hosted open-source model (Ollama, vLLM) | €0 in API fees (server cost only) | |
Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of October 13, 2026. Estimate: 1 token ≈ 3.6 characters.
Common to all 3 regions
Created by the author, no outside source.
Commercial use allowed · credit the author · changes allowed.
Text or data only: no access to files, network or commands.
Hosted in France (Scaleway, Paris). No transfer outside the EU.
European Union · 5/5
No personal data.
No training data: no summary required.
United States · 5/5
No personal data.
No training data: no documentation to publish.
China · 5/5
No personal data.
No training data; AI-generated content published in China must be labelled (2025).
Indicative summary as of 30/09/2026, not a legal certification. Method and sources →
Content quality
Performance not measured: no measured speed and no passed test
The detailed criteria are for members.
Every criterion, the points removed and a tip to fix each one.
Content analysis
The detailed criteria are for members.
Every criterion, the points removed and a tip to fix each one.
Computed from the content of the resource, by rules, without AI. The score is in the Quality tab.
MCP contexte
https://contextetech.com/mcp
load 1rcm91j
Add the URL as a connector in your AI apps' settings, then send the request above.
API
import json, urllib.request url = "https://contextetech.com/api/resources/contextetech--mistral-7b-ollama-mac-16gb" fiche = json.load(urllib.request.urlopen(url)) print(fiche["title"] or fiche["name"])
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
Create the model (Ollama)
# enregistrez le Modelfile, puis : ollama create mistral-7b-ollama-mac-16gb -f Modelfile ollama run mistral-7b-ollama-mac-16gb
Community
No comments yet. Share your feedback, it will help the next person.