Mistral 7B auf einem Mac mit 16 GB und Ollama
Ollama-Modelfile, um Mistral 7B Instruct lokal auf einem Mac mit 16 GB zu betreiben: Q4-Quantisierung, 8k Kontext, Antworten auf Deutsch.
| Model | mistral:7b-instruct-q4_K_M |
|---|---|
| Tested hardware | Mac mit Apple Silicon und 16 GB Arbeitsspeicher |
Modelfile
FROM mistral:7b-instruct-q4_K_M PARAMETER num_ctx 8192 PARAMETER temperature 0.3 SYSTEM """Du bist ein Assistent, der klar und knapp auf Deutsch antwortet. Wenn du etwas nicht weißt, sag es."""
Launch command
ollama create mistral-de -f Modelfile && ollama run mistral-de
Estimated cost
Input tokens per call : ≈ 198
| Model | Per call | Per 1,000 calls |
|---|---|---|
| Mistral Large · Mistral AI | €0.00009 | €0.09 |
| DeepSeek Flash · DeepSeek | €0.00005 | €0.05 |
| DeepSeek V4 Pro · DeepSeek | €0.00023 | €0.23 |
| GPT-6 Luna · OpenAI | €0.00002 | €0.02 |
| GPT-6 Sol · OpenAI | €0.00035 | €0.35 |
| Claude Sonnet 5.5 · Anthropic | €0.00035 | €0.35 |
| Claude Opus 5.5 · Anthropic | €0.00070 | €0.70 |
| 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 September 29, 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 →
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.
- Identifier
- contextetech--mistral-7b-ollama-mac-16gb-de
- Type
- Inference configs
- File
- Modelfile
- Format
- MODELFILE
- Size
- 195 bytes
- Encoding
- UTF-8
- Estimated tokens
- ≈ 54
- Language
- German
- License
- MIT
- Commercial use
- Allowed
- Personal data
- None
- Version
- 1.0
- Published on
- October 3, 2026 at 5:20 AM
- Updated on
- October 3, 2026 at 5:20 AM
- Storage
- in database
- Uses
- 0
- Likes
- 0
Modelfile
FROM mistral:7b-instruct-q4_K_M PARAMETER num_ctx 8192 PARAMETER temperature 0.3 SYSTEM """Du bist ein Assistent, der klar und knapp auf Deutsch antwortet. Wenn du etwas nicht weißt, sag es."""
Launch command
ollama create mistral-de -f Modelfile && ollama run mistral-de
Create the model (Ollama)
# enregistrez le Modelfile, puis : ollama create mistral-7b-ollama-mac-16gb-de -f Modelfile ollama run mistral-7b-ollama-mac-16gb-de
Community
No comments yet. Share your feedback, it will help the next person.