📄 文章列表
134 篇文章
AlphaSignal
Google Shrinks Gemma 4 to Under 1GB Without Losing Reasoning Power | AlphaSignal
AlphaSignal
Google Shrinks Gemma 4 to 1GB so It Runs on Your Phone | AlphaSignal
AlphaSignal
Google's Gemma 4 12B Runs Text, Images and Audio on a 16GB Laptop | AlphaSignal
AlphaSignal
Google's DiffusionGemma Generates Text 4x Faster by Ditching Sequential Tokens | AlphaSignal
AlphaSignal
Google's DiffusionGemma Generates 256 Tokens at Once, 4x Faster Than Any LLM | AlphaSignal
AlphaSignal
Google Drops Six AI Releases Including Gemma 4 12B Running on a Laptop | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 QAT Slashes Memory 72% for Local Deployment | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 Now Runs a 26B Model on a 16GB Laptop | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 12B Runs Multimodal AI on Your Laptop for Free | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 12B Runs Fully Offline on Any 16GB Laptop | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 12B Runs Full Multimodal AI on a 16GB Laptop | AlphaSignal
AlphaSignal
Google DeepMind's DiffusionGemma Hits 1,000+ Tokens per Second on a Single GPU | AlphaSignal
AlphaSignal
Google DeepMind's DiffusionGemma Hits 1,000 Tokens per Second by Ditching Left-to-Right Generation | AlphaSignal
AlphaSignal
Google and Hugging Face Race Gemma 4 Past 127 Tokens per Second | AlphaSignal
AlphaSignal
Cohere's North Mini Code Beats Models 40x Larger at Agentic Coding | AlphaSignal
AlphaSignal
Cerebras Runs Gemma 4 at 1,500 Tokens per Second, 15x Faster Than Haiku | AlphaSignal
AlphaSignal
Artificial Analysis Ranks 20 AI Safety Guards and WildGuard Wins | AlphaSignal
TDS
A Three-Phase Factual Recall Circuit in Gemma-2B and Gemma-12B-IT
TDS
From Local LLM to Tool-Using Agent
TDS