Google releases Gemma 3n: 2GB RAM multimodal model, first sub-10B to top 1300 on LMArena
joemeno · x · 2026-09-17
Google has officially launched Gemma 3n:
- Multimodal understanding: handles text, audio, image, and video input
- Ultra-light: runs with as little as 2GB of RAM
- Benchmark: first model under 10B to score above 1300 on LMArena
Available now on Hugging Face, Kaggle, llama.cpp, Google AI Studio, and more.
More from Models
- OpenRouter's Mystery Union Model Reverse-Engineered: Likely a Qwen4 MoE — unsane_imagination · 2026-09-17
- New Model Jev Runs Security Pipelines 5x Cheaper and Faster, Devs Say — zeeg · 2026-09-17
- API users have zero loyalty: LLM market share could flip from 80-20 to 20-80 overnight — tengyanAI · 2026-09-17
- LAB legal benchmark flaw: case docs leak planted issues directly to models — andersonbcdefg · 2026-09-17
- MiMo eval chart shows judge and probe disagree 60% of the time, sparking reward-hacking concerns — andrew_n_carr · 2026-09-17
- Fans mourn the end of Codex lead's regular daily reset cadence — kimmonismus · 2026-09-17