/ Models

Language models

granite-embedding

Runs on your Mac · granite-embedding

Runs on your own machine — free, offline, no key, and no cloud API for it here.

free embedding

The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.

Install on 00

Get the 00 app

Free · macOS

Your agents, your models, your machine — this model installs with one click once the app is on board.

Download free →

What it costs

Input / 1M
free
Output / 1M
free
1M in + 1M out
free

Free to run — downloads once from the Ollama library, then runs on your own Mac with no per-token cost. It costs you disk, memory and time instead — none of which the library states.

What it can do

Takes
text
Does
makes embeddings
Sizes to pull
30m · 278m
Context window
Download size
Released

Blank because the library states none of them. Sizes are parameter counts, not disk size — memory depends on the quantisation you pull.

Run it

In the 00 app — pick it from the local models and the app pulls it; then it answers with no key, no account, no network. Get 00.

In a terminal — with Ollama installed:

ollama pull granite-embedding

Add a size for a specific build — granite-embedding:30m, granite-embedding:278m. Without one you get the default tag.

It runs on your machine: no AI tokens billed, and it does not answer at the hosted endpoints. See it in the Ollama library · ← all models