← All modelsEVIDENCE-LABELLED PROFILE · REVIEWED 2026-08-24

All MiniLM 22M

A very small sentence embedding model for fast local search. It is not a chat model.

Officially supported35/100 · Experimental confidence

The official artifact path was checked. Memory is a conservative planning estimate; speed and output quality require a test on the target device.

  • Official model source
  • Official engine artifact
LOCALLENS RAM FLOOR7 GB
ARTIFACT SIZE~0.046 GB
INPUTText
LICENCEApache 2.0

Will it run?

LocalLens uses 7 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?

EmbeddingsRAGSearch

Suggested Ollama artifact

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

ollama pull all-minilm:22m

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: Short sentence embedding input. The source establishes specifications; it does not guarantee that maximum context fits at the LocalLens minimum RAM floor.