가이드로
MODEL / META

Llama 3.2 3B

Long advertised context still increases KV-cache memory; use modest context on small devices.

1차 출처
총 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
OllamaEasyollama run llama3.2:3b
llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080
LM StudioEasySearch “meta-llama/Llama-3.2-3B-Instruct” → Load a Q4/INT4 build → Start Server
MLX LMMediummlx_lm.chat --model meta-llama/Llama-3.2-3B-Instruct
주의

Long advertised context still increases KV-cache memory; use modest context on small devices.