MODEL / GOOGLE

Gemma 3 27B

Google's 24 GB fit example is for the INT4 variant and excludes some runtime overhead.

총 파라미터27B

추정 메모리~20.5 GBINT4

컨텍스트128KText + Image

LicenseGemma140+ languages

01 / 추천 용도

02 / 추정 적합도

03 / 배포 환경

OllamaEasyollama run gemma3:27b

llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080

LM StudioEasySearch “google/gemma-3-27b-it” → Load a Q4/INT4 build → Start Server

MLX LMMediummlx_lm.chat --model google/gemma-3-27b-it

주의

Google's 24 GB fit example is for the INT4 variant and excludes some runtime overhead.