MODEL / META
Llama 3.2 3B
Long advertised context still increases KV-cache memory; use modest context on small devices.
Fuente primariaParámetros totales3B
Memoria estimada~2.8 GBGGUF Q4
Contexto128KText
LicenseLlama 3.2 Community8 official languages
01 / IDEAL PARA
- chat
- summaries
- mobile
02 / COMPATIBILIDAD ESTIMADA
03 / EJECUTAR CON
OllamaEasy
ollama run llama3.2:3bllama.cppMedium
llama-server -m /path/to/verified-model.gguf --port 8080LM StudioEasy
Search “meta-llama/Llama-3.2-3B-Instruct” → Load a Q4/INT4 build → Start ServerMLX LMMedium
mlx_lm.chat --model meta-llama/Llama-3.2-3B-InstructAtención
Long advertised context still increases KV-cache memory; use modest context on small devices.