Llama 3.2 3B Instruct Abliterated
Uncensored via refusal ablation on Llama 3.2 3B Instruct
131K contextiPhone & iPad · Mac
Local Llama 3.2 3B Models for iPhone, iPad & Mac
Run Llama 3.2 3B models fully offline on iPhone, iPad & Mac inside Private LLM — private, with nothing sent to a server.
6 models
FuseChat Llama 3.2 3B Instruct
General assistant fusing source models for improved instruction following
131K contextiPhone & iPad · Mac
Hermes 3 Llama 3.2 3B
General-purpose assistant with reliable function calling and JSON outputs
131K contextiPhone & iPad · Mac
Meta Llama 3.2 3B Instruct
General-purpose model in the Llama 3.2 3B family
iPhone & iPad · Mac
Dolphin 3.0 Llama 3.2 3B
Uncensored Llama 3.2 3B instruct with user-defined alignment and 131K context
131K contextiPhone & iPad · Mac
Llama 3.2 3B Instruct Uncensored
Uncensored Llama 3.2 3B modification that bypasses refusal mechanisms
131K contextiPhone & iPad · Mac
Frequently asked questions
Private LLM runs Llama 3.2 3B models on iPhone, iPad & Mac, fully on-device. Larger variants like Llama 3.2 3B Instruct Abliterated, FuseChat Llama 3.2 3B Instruct, Hermes 3 Llama 3.2 3B need more memory, so the right pick depends on your device's RAM.
Yes. Every Llama 3.2 3B model runs entirely on your Apple device inside Private LLM — no cloud, no logging, and nothing sent off-device.
Only the one-time download needs a connection. After that, every Llama 3.2 3B model runs 100% offline in Private LLM.