Gemma · AI Beat

06 Jun 2026 · AI Beat Desk

Training the Compression In: Gemma 4 QAT for Mobile

Google released quantization-aware training checkpoints for Gemma 4 with a new mobile-specific format — channel-wise quantization aligned with NPU memory layouts, 2-bit compression for token generation layers, pre-calculated scaling constants — bringing the Gemma 4 E2B text model under 1 GB of memory.

06 May 2026 · AI Beat Desk

Gemma 4 Gets Speculative Decoding That Ships

Google ships multi-token prediction draft models for the full Gemma 4 family under Apache 2.0, reporting up to 3x throughput gains. The architecture is tightly coupled — shared embeddings, last-layer activations — which keeps the drafter accurate but limits reuse. MoE variants complicate the picture.