Llama 3.2 1B

mobile-small

Compact Llama for mobile. Good extraction quality with low resource use.

Parameters1.0B
Context131,072 tokens
Download0.7 GB
Min RAM4 GB
Architecturellama

Available quantizations

QuantSizeQuality
Q4_K_M0.7 GBgood
Q5_K_M0.8 GBbetter
Q8_01.3 GBbest

About this model

By Meta

Meta's smallest Llama 3.2 — built for on-device use. Quick summaries, short chats, and lightweight tasks on hardware where bigger models won't fit.

What it's good at

  • Extraction — Reliable at pulling structured facts out of text.
  • Classification — Good at labeling and routing text.
  • Tool use — Not tuned for tool use — better as a reasoning or chat model.
  • Draft model — Small and fast — a good speculative-decoding draft model.

Real-world performance

Runs great on M1 · 16 GB RAM, M5 Max · 128 GB RAM — 30–240 tok/s.

Running it with llama.cpp

  • Q4_K_M is the sweet spot for most machines; Q8_0 squeezes out the best quality if you have the RAM to spare.

License: Meta Llama 3.2 License

Built with Llama

Check whether your machine can run this model — with real measured speeds from anonymous community benchmarks — on the Central-Intel compatibility page.