← All modelsEVIDENCE-LABELLED PROFILE · REVIEWED 2026-10-20

Ministral 3 8B

A Mistral assistant for text, image questions, multilingual work and tools. Start with a short context and check its memory use on your computer.

Officially supported35/100 · Experimental coverage

Exact local Ollama manifest and configuration checked on 2026-10-20. Memory figures are conservative planning estimates; no DeviceTerra inference or speed test is claimed. Requires Ollama 0.13.1 or newer. Requires Ollama 0.13.1 or newer. Published parameter tier; image inputs also consume memory.

  • Official model source
  • Official engine artifact
MAMILENS RAM FLOOR17 GB
ARTIFACT SIZE~6.03 GB
INPUTText + Image
LICENCEApache 2.0

Will it run?

MamiLens uses 17 GB as a conservative planning floor for this profile and its listed quantization. This is not measured speed. Processor, backend support, context length, memory bandwidth and other applications still affect the result.

Check your complete system →

What is it useful for?

GeneralWritingVisionToolsMultilingual

Suggested Ollama artifact

Confirm the tag on the official page before downloading, then run:

ollama run ministral-3:8b

Start with a representative non-sensitive task. Record the exact runtime, quantization, context, load time, generation speed, memory use and answer quality.

Evidence and limits

Published context: 256K artifact maximum; practical context depends on memory. The source establishes specifications; it does not guarantee that maximum context fits at the MamiLens minimum RAM floor.