MODEL / GOOGLE
Gemma 3 1B
Small and efficient, but not a substitute for larger reasoning models.
Source primaireParamètres totaux1B
Mémoire estimée~1.4 GBINT4 / GGUF Q4
Contexte32KText
LicenseGemma140+ languages
01 / IDÉAL POUR
- classification
- summaries
- edge
02 / COMPATIBILITÉ ESTIMÉE
03 / DÉPLOYER AVEC
OllamaEasy
ollama run gemma3:1bllama.cppMedium
llama-server -m /path/to/verified-model.gguf --port 8080LM StudioEasy
Search “google/gemma-3-1b-it” → Load a Q4/INT4 build → Start ServerMLX LMMedium
mlx_lm.chat --model google/gemma-3-1b-itAttention
Small and efficient, but not a substitute for larger reasoning models.