ガイドへ戻る
MODEL / GOOGLE

Gemma 3 4B

Vision support depends on runtime and projector compatibility.

一次情報
総パラメータ4B
推定メモリ~4.2 GBINT4 / GGUF Q4
コンテキスト128KText + Image
LicenseGemma140+ languages
01 / 用途
  • vision
  • document Q&A
  • multilingual chat
02 / 推定適合
03 / 実行環境
OllamaEasyollama run gemma3:4b
llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080
LM StudioEasySearch “google/gemma-3-4b-it” → Load a Q4/INT4 build → Start Server
MLX LMMediummlx_lm.chat --model google/gemma-3-4b-it
注意

Vision support depends on runtime and projector compatibility.