Tag: LLM
All the articles with the tag "LLM".
-
GPT-5.5 vs Claude Opus 4.6 vs Gemini 2.5 Pro: Coding Capability Comparison 2026
A 2026 head-to-head coding comparison of the leading large language models: benchmark numbers, pricing, and real-world coding performance for GPT-5.5, Claude Opus 4.6, and Gemini 2.5 Pro — to help you pick the right model for everyday development.
-
What Qwen3.6-Plus Tells Us: Chinese LLMs Can Now Compete in Specific Domains
Alibaba's Qwen3.6-Plus topped OpenRouter's global daily leaderboard just one day after launch, and Chinese AI token usage has now outpaced the US for five straight weeks. What does this actually mean? This post breaks it down across technology, data, and ecosystem.
-
Flash-MoE: Running a 397B-Parameter Model on a MacBook at 4.4 token/s
A developer built Flash-MoE in 24 hours: it runs the 397B-parameter Qwen3.5 model on a 48GB MacBook Pro at 4.4 token/s, using only about 6GB of RAM and no cloud GPUs. We break down how it works: SSD streaming, Metal shader optimization, and MoE sparse activation.
-
Reading the MCP 2026 Roadmap: From Local Tools to Production-Grade Agent Infrastructure
MCP (Model Context Protocol) has published its 2026 roadmap with four priority areas: transport evolution, agent communication, governance maturity, and enterprise readiness. A technical breakdown of the concrete problems and proposed solutions in each area.
-
The 2026 AI Model Landscape: Hands-On Comparison of 12 Leading Models from China and Abroad
Hands-on benchmarks of 12 AI models (GPT-4o, Claude 3.5, Gemini 2.0, Qwen 2.5, GLM-4, Kimi, and more) across 6 real-world scenarios including code generation, Chinese writing, and reasoning. Includes performance scores, monthly cost comparisons, and a decision tree to help you pick the right model.
-
Building AI Agents with Long-Term Memory: From Design Patterns to Production
A deep dive into building episodic, semantic, and procedural long-term memory for AI Agents, with a complete technical architecture, code implementation, and production optimization strategies.
-
AI Agent Memory Systems in Practice: OpenClaw Memory Best Practices
A deep dive into OpenClaw's memory architecture, from file layout to retrieval tuning, with actionable best practices for managing AI Agent memory