Gemma
Google’s first lightweight open models, released in 2B and 7B sizes.
FAMILY / GOOGLE DEEPMIND
Gemma
Google’s open-model family for local, edge, and customizable deployment.
- First model
- 2024
- Models
- 8
- Latest
- DiffusionGemma 26B
01 / LINEAGE MAP
Model lineage
predecessor derived from
02 / GENERATIONS
What changed
Gemma 2 27B
Raised reasoning quality in 9B and 27B sizes designed for accessible accelerators.
Gemma 3 27B
Added image input, a 128K context window, and support for more than 140 languages.
Gemma 3n E4B
Used MatFormer and Per-Layer Embeddings to bring multimodal understanding to mobile devices.
Gemma 4 31B
The high-quality dense Gemma 4 flagship for local reasoning, coding, and agent workflows.
Gemma 4 26B MoE
The Gemma 4 MoE activating only 3.8B parameters per step for local speed and intelligence density.
Gemma 4 12B
A unified encoder-free multimodal model for laptops, filling the gap between E4B and 26B.
DiffusionGemma 26B
An experimental Gemma 4 text-diffusion model exploring lower latency through parallel block generation.