Mistral 7B su un Mac da 16 GB con Ollama

Modelfile Ollama per eseguire Mistral 7B Instruct in locale su un Mac da 16 GB: quantizzazione Q4, contesto 8k, risposte in italiano.

Modelfile

FROM mistral:7b-instruct-q4_K_M
PARAMETER num_ctx 8192
PARAMETER temperature 0.3
SYSTEM """Sei un assistente che risponde in italiano, in modo chiaro e conciso.
Se non lo sai, dillo."""

Launch command

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

Estimated cost

Input tokens per call : ≈ 192

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.

Identifier

contextetech--mistral-7b-ollama-mac-16gb-it

Type

Inference configs

File

Modelfile

Format

MODELFILE

Size

186 bytes

Encoding

UTF-8

Estimated tokens

≈ 52

Language

Italian

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 """Sei un assistente che risponde in italiano, in modo chiaro e conciso.
Se non lo sai, dillo."""

Launch command

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

Create the model (Ollama)

# enregistrez le Modelfile, puis :
ollama create mistral-7b-ollama-mac-16gb-it -f Modelfile
ollama run mistral-7b-ollama-mac-16gb-it