by Meta AI

Llama 3.2 1B.

text open weights edge 1B params 128K ctx Transformer
Cheapest input
$0.06/M
on Together AI
Cheapest output
$0.06/M
on Together AI
Smallest GPU
1× Nvidia GeForce GTX 1660 Super
$0.029/hr
Description

About Llama 3.2 1B.

Llama 3.2 1B is Meta's smallest Llama variant — designed for on-device deployment (mobile, browser via WebGPU, IoT). Runs in <2 GB RAM at INT4. Surprisingly competent at simple chat and classification despite the tiny size; the headline target was mobile partners like Qualcomm and MediaTek.

Architecture

How it's built.

Architecture
Transformer
Knowledge cutoff
Dec 2023
269 days from cutoff to release.
Context window

How much it can remember.

128K tokens ≈ 96,000 English words
4K 32K 128K 1M
Capabilities

What it can do.

· Vision input
· Audio input
· Video input
· Function calling
· Tool use
· JSON mode
✓ Streaming
✓ Fine-tuning