DiffusionGemma: 4x Faster Text Generation (blog.google)

Screenshot of blog.google: DiffusionGemma: 4x Faster Text Generation

First screen, captured 4 months ago.

Looks similar

Screenshot of blog.google: Accelerating Gemma 4: faster inference with multi-token prediction drafters

Accelerating Gemma 4: faster inference with multi-token prediction drafters (blog.google)

640 points by amrrs 5 months ago | 309 comments

Google blog post announcing Multi-Token Prediction drafters for Gemma 4 models to reduce inference latency and improve responsiveness.

gemma-4 multi-token-prediction speculative-decoding llm-inference

Screenshot of blog.google: Gemma 4 12B: A unified, encoder-free multimodal model

Gemma 4 12B: A unified, encoder-free multimodal model (blog.google)

1007 points by rvz 4 months ago | 379 comments

Google blog post announcing Gemma 4 12B, an encoder-free multimodal model designed to run on laptops with mobile-first efficiency and advanced reasoning.

gemma google multimodal-models open-weights

Screenshot of blog.google: Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency

Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency (blog.google)

384 points by theanonymousone 4 months ago | 120 comments

Google blog post announcing Gemma 4 models trained with Quantization-Aware Training to cut memory use and improve on-device performance on mobile and laptops.

gemma-4 quantization-aware-training google on-device-ai

Screenshot of blog.google: T5Gemma 2: The next generation of encoder-decoder models

T5Gemma 2: The next generation of encoder-decoder models (blog.google)

137 points by milomg 10 months ago | 25 comments

Screenshot of blog.google: DolphinGemma: How Google AI is helping decode dolphin communication

DolphinGemma: How Google AI is helping decode dolphin communication (blog.google)

316 points by alphabetting 1 year ago | 123 comments

Screenshot of blog.google: Gemini CLI: your open-source AI agent

Gemini CLI: your open-source AI agent (blog.google)

16 points by sunaookami 1 year ago | 0 comments

Looks similar

Accelerating Gemma 4: faster inference with multi-token prediction drafters(blog.google)

Gemma 4 12B: A unified, encoder-free multimodal model(blog.google)

Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency(blog.google)

T5Gemma 2: The next generation of encoder-decoder models(blog.google)

DolphinGemma: How Google AI is helping decode dolphin communication(blog.google)

Gemini CLI: your open-source AI agent(blog.google)