gemma — AI Digest

4 июн Google DeepMind Releases Gemma 4 12B: Encoder-Free Multimodal Model That Runs on a 16 GB Laptop Google DeepMind models-llm
11 июн Google Releases DiffusionGemma: 26B Open Model with 4× Faster Text Generation Google DeepMind models-llm
8 июн Google DeepMind Releases Gemma 4 QAT Checkpoints: Sub-1 GB On-Device E2B Model Google DeepMind models-llm
17 июн vLLM v0.23.0: Model Runner V2 Default for Llama and Mistral, Transformers v5, Multi-Tier KV Cache tools
6 мая Ollama v0.23.1: Gemma 4 MTP Speculative Decoding Delivers 2× Speed on Apple Silicon tools
2 июл Ollama v0.31.1: Gemma 4 Nearly 90% Faster on Apple Silicon via MTP Ollama tools