DiffusionGemma: 4x faster text generation★ 74
Google DeepMind Blog4 days agoReleaseGoogle’s DiffusionGemma is an Apache 2.0 experimental open model using text diffusion instead of standard autoregressive decoding. The 26B MoE model activates 3.8B parameters during inference and is designed for low-latency local workflows. Google claims up to 4x faster generation on dedicated GPUs, while noting that output quality is below standard Gemma 4 and production-quality use cases should still prefer Gemma 4.
Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency★ 72
Hacker News (AI keywords)9 days agoReleaseGoogle released new Gemma 4 checkpoints optimized with Quantization-Aware Training to preserve quality after compression. The release includes Q4_0 checkpoints and a mobile-focused quantization format that can reduce Gemma 4 E2B memory use to about 1GB, or below 1GB for a text-only configuration. The models are available through Hugging Face and supported across llama.cpp, Ollama, LM Studio, LiteRT-LM, Transformers.js, SGLang, vLLM, MLX, and Unsloth.