What changed under the hood:
• Vision. Replaced the encoder with a lightweight embedding module (single matrix multiply + positional embedding + normalization). The LLM backbone now handles visual processing directly
• Audio. Encoder removed entirely. Raw audio signal is projected straight into the same token space as text
• Inference. Ships with multi-token prediction (MTP) drafters for speculative decoding, cutting latency
Benchmarks (Gemma 3 27B / Gemma 4 12B / Gemma 4 26B):
- GPQA Diamond: 44 / 78.8 / ~80
- BBEH: 18 / 53 / 62 MMLU Pro: 67 / 77.2 / 78
- LiveCodeBench: 28 / 72 / 76
- DocVQA: 83 / 94.9 / 93
- InfoVQA: 60 / 88.4 / 90
- MMMU Pro: 65 / 69.1 / 72
Runs locally on consumer laptops with 16GB VRAM or unified memory – including MacBook M-series
Demo source: Google
Gemma 4 12B delivers great performance with a small memory footprint and a novel architecture. pic.twitter.com/aUyX7lzj9f
— Google (@Google) June 3, 2026