MODEL / META
Llama 3.2 3B
Long advertised context still increases KV-cache memory; use modest context on small devices.
1차 출처총 파라미터3B
추정 메모리~2.8 GBGGUF Q4
컨텍스트128KText
LicenseLlama 3.2 Community8 official languages
01 / 추천 용도
- chat
- summaries
- mobile
02 / 추정 적합도
03 / 배포 환경
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-Instruct주의
Long advertised context still increases KV-cache memory; use modest context on small devices.