Llama 3.2 3B
smallFast and lightweight. Good for quick tasks and low-resource devices.
Parameters3.0B
Context131,072 tokens
Download2.0 GB
Min RAM4 GB
Architecturellama
Available quantizations
| Quant | Size | Quality |
|---|---|---|
| Q4_K_M | 2.0 GB | good |
| Q5_K_M | 2.3 GB | better |
| Q8_0 | 3.4 GB | best |
Check whether your machine can run this model — with real measured speeds from anonymous community benchmarks — on the Central-Intel compatibility page.