/ Models

Language models

smollm

Runs on your Mac ยท smollm

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

free

๐Ÿช A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.

Install on 00

Get the 00 app

Free · macOS

Your agents, your models, your machine โ€” 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 โ€” 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 โ€” none of which the library states.

What it can do

Takes
text
Does
answers in text
Sizes to pull
135m ยท 360m ยท 1.7b
Context window
โ€”
Download size
โ€”
Released
โ€”

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

Run it

In the 00 app โ€” 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 โ€” with Ollama installed:

ollama pull smollm

Add a size for a specific build โ€” smollm:135m, smollm:1.7b. 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 ยท โ† all models