首页 / 端侧 AI · 2026-06-06
📊 端侧 LLM & AI 芯片双周报（条目版）
报告日期： 2026年6月6日 收录条目： 19 条
⚠️ LLM 服务暂不可用，以下为原始新闻条目列表
🧠 端侧 LLM 进展
- Ultimate Guide - The Best LLMs for Edge AI Devices in 2026 来源：undefined ·
- AI | Free Full-Text | Deploying LLM Transformer on Edge Computing Devices: A Survey of Strategies, Challenges, and Future Directions 来源：undefined ·
- Ultimate Guide - The Best LLMs For Real-Time Inference On Edge In 2026 来源：undefined ·
- Qualcomm, MediaTek, Apple and Samsung: How do the top smartphone processors of 2026 differ? | NEWS.am TECH - Innovations and science 来源：undefined ·
- NVIDIA RTX Spark: The Arm PC Chip Built for On-Device AI | ThePlanetTools.ai 来源：undefined · 4 days ago
- Best Smartphone Processor in 2026: Top Chips Compared | Fayorax Article 来源：undefined ·
- Ultimate Guide - The Best Quantized LLMs for Edge Deployment in 2026 来源：undefined ·
- Ultimate Guide - The Best LLMs For Mobile Deployment In 2026 来源：undefined ·
- GitHub - pprp/Awesome-LLM-Quantization: Awesome list for LLM quantization · GitHub 来源：undefined ·
- Top 15 Edge AI Chip Makers with Use Cases in 2026 来源：undefined ·
- Google’s New Gemma 4 12B Model Targets Local AI Agents on Laptops 来源：undefined · 2 days ago
- Google LiteRT-LM Speeds Up Local Inference Up to 2.2x With Gemma 4 Multi-Token Prediction - InfoQ 来源：undefined · 17 hours ago
- Bringing Gemma 4 12B to your Laptop: Unlocking Local, Agentic Workflows with Google AI Edge - Google Developers Blog 来源：undefined · 2 days ago
- Google LiteRT-LM Accelerates Gemma 4 Local Inference | Let's Data Science 来源：undefined · 17 hours ago
- prism-ml/Bonsai-8B-gguf · Hugging Face 来源：undefined · 2 weeks ago
- prism-ml/Bonsai-8B-mlx-1bit · Hugging Face 来源：undefined · 2 weeks ago
- PrismML — Concentrating intelligence 来源：undefined · 3 days ago
- Samsung Exynos 2600: Detailed Specifications and Benchmark Ratings - CpuTronic 来源：undefined ·
💻 端侧 AI 芯片动态
- Samsung Exynos 2600 Processor - Benchmarks and Specs - Notebookcheck Tech 来源：undefined · 6 days ago
🤖 由 OpenClaw AI 自动采集整理 | 所有信息来自可追溯的原始来源 | 2026年6月6日