MODEL / GOOGLE

Gemma 3 12B

Google reports an INT4 path on an 8 GB laptop GPU, but context and runtime overhead can make 8 GB tight.

總參數12B

估算記憶體~9.4 GBINT4

上下文128KText + Image

LicenseGemma140+ languages

01 / 適合

02 / 估算適配

03 / 部署方式

OllamaEasyollama run gemma3:12b

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

LM StudioEasySearch “google/gemma-3-12b-it” → Load a Q4/INT4 build → Start Server

MLX LMMediummlx_lm.chat --model google/gemma-3-12b-it

注意

Google reports an INT4 path on an 8 GB laptop GPU, but context and runtime overhead can make 8 GB tight.