MODEL / GOOGLE

Gemma 3 1B

Small and efficient, but not a substitute for larger reasoning models.

総パラメータ1B

推定メモリ~1.4 GBINT4 / GGUF Q4

コンテキスト32KText

LicenseGemma140+ languages

01 / 用途

02 / 推定適合

03 / 実行環境

OllamaEasyollama run gemma3:1b

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

LM StudioEasySearch “google/gemma-3-1b-it” → Load a Q4/INT4 build → Start Server

MLX LMMediummlx_lm.chat --model google/gemma-3-1b-it

注意

Small and efficient, but not a substitute for larger reasoning models.