#Sparse MoE

178 related articles

Jul 25, 2026·6 min

How the Creator of Redis Squeezed a 284-Billion-Parameter DeepSeek Into an Ordinary Laptop

Redis author antirez built the pure-C inference engine DS4 "Dwarf Star," compressing DeepSeek V4 Flash from 500GB to 80.8GB via asymmetric quantization for local deployment on 128GB unified memory at 26.7 tokens/sec.

Jul 25, 2026·3 min

The T-Parameter Era of Open-Source LLMs: Four Chinese AI Companies Break the Trillion-Parameter Barrier

Moonshot AI, Alibaba, DeepSeek, and Meituan all crossed the trillion-parameter threshold. China's open-source LLMs made the B-to-T leap in just 18 months.

Jul 24, 2026·4 min

Complete Guide: Connecting DeepSeek and Other Chinese LLMs to Codex

No ChatGPT account? No problem. Learn how to connect DeepSeek and other Chinese LLMs to Codex using the Codex++ management tool — including Base URL setup, API Key creation, and token top-up.

Jul 24, 2026·4 min

jlens-gguf: Bringing Jacobian Lens Visualization and Steering to llama.cpp Local LLMs

jlens-gguf is an open-source tool bringing Anthropic's Jacobian Lens interpretability method to GGUF and llama.cpp, enabling internal observation, real-time steering, and abliteration for both dense and MoE models.

Jul 24, 2026·3 min

DeepSeek's In-House AI Chip: A Critical Step Toward Breaking China's NVIDIA Dependence

DeepSeek is reportedly developing its own AI chip, moving from algorithms to hardware to achieve software-hardware co-optimization. An in-depth analysis of its strategic rationale, key challenges, and implications for China's AI industry autonomy.

Jul 24, 2026·7 min

DeepSeek's Mysteriously Retracted Paper: Breaking AI's Multimodal Reasoning Bottleneck with Visual Primitives

DeepSeek's paper 'Thinking with Visual Primitives' was online for just 4 hours before being pulled. It uses bounding boxes and points as reasoning primitives, letting models 'point at' images to outperform GPT, Gemini, and Claude on maze navigation and counting.

Jul 23, 2026·8 min

LangChain Crash Course: A Complete Roadmap from Zero to Agent Development

A systematic roadmap from LangChain and LangGraph to multi-agent development, covering RAG, Tool Calling, MCP, and more, helping developers break into AI app development.

Jul 23, 2026·3 min

Qwen3.8 Deep Dive: How Does a 2.4 Trillion Parameter MoE Model Claim Second Place?

Alibaba's Qwen3.8 challenges larger models with a 2.4T-parameter MoE architecture, claiming second only to Gemini. A deep dive into MoE mechanics, continuous updates, two-speed release strategy, and real local deployment requirements.

Jul 23, 2026·6 min

Hands-On with Qwen 3.8 Max: How an Open-Source Model Closes In on Top-Tier Closed Models

Qwen 3.8 Max has 2.4 trillion parameters and will be open-sourced. In KingBench testing it scored 81.25%, ranking second, beating Claude Opus 4.8 and trailing only Fable 5. A deep dive into its performance across 8 tests.

Jul 23, 2026·3 min

Alibaba's 2.4 Trillion Parameter Qwen Model: Separating Technical Substance from Marketing Hype

Alibaba's Qwen releases a 2.4T parameter MoE model claiming to be 'second only to Gemini 2.5.' We break down what's real—and what's just hype.

Jul 23, 2026·7 min

Qwen3 235B A22B in Practice: A 2.4-Trillion-Parameter Open Model Surpasses Claude Opus

Hands-on with Alibaba Tongyi Qianwen's strongest Qwen3: a 2.4-trillion-parameter open weight model scoring 81.25% on KingBench, ranking second and beating Claude Opus 4.8 with perfect scores in game dev, math, and agent tasks.

Jul 23, 2026·7 min

AI Daily: T-Head Open-Sources SAIL Software Stack at WAIC, Flurry of Large Model Releases

T-Head open-sources AI software stack T-Head SAIL at WAIC to lower the barrier for domestic chip development; Kimi K3 tops the WebDev leaderboard; Qwen 3.8 Max Preview cuts prices aggressively; Moonshot prepares a Hong Kong IPO; and Oracle switches its data center to a fuel cell microgrid.

Jul 23, 2026·7 min

Alibaba Open-Sources 2.4T Qwen Model as Chinese AI Sweeps the Global Competitive Landscape

Alibaba open-sources a 2.4 trillion parameter Qwen model and launches the Qwen Token Plan. Chinese models surge, Kimi K3 tops global rankings, and China's AI is reshaping the global competitive landscape.

Jul 22, 2026·3 min

Kimi K3 Hands-On: How a 2.8-Trillion-Parameter Open-Source Model Beat Fable5

A US engineer's live test of Kimi K3: 2.8T parameters, 1M token context, 87% audience vote over Fable5 in game generation. Full report covering benchmarks, speed, and code debugging.

Jul 22, 2026·4 min

UK Sovereign AI: How Cosine AI Is Punching Above Its Weight Against American Compute Dominance

Cosine AI founder reveals how the UK's first sovereign LLM is being built — from government compute grants and RL credit attribution to multi-agent orchestration and synthetic data pipelines.

Jul 21, 2026·3 min

27B Parameter LLM on an iPhone? A Deep Dive into On-Device Full-Parameter AI

Startup Prismo claims to compress a 27B-parameter model to 4GB for full local inference on iPhone 17 Pro. We break down the compression tech, compare it to Apple's MoE approach, and assess real-world limits.

Jul 21, 2026·3 min

Ornith 9B/35B Hands-On: A New Local Deployment Option for Code Agents

Ornith 1.0 by Deep Reinforce reinforces Qwen 3.5 for code agents. We test Ornith 9B & 35B MoE on Chinese writing, logic, and invoice OCR, with full llama.cpp deployment guide.

Jul 21, 2026·2 min

MiniMax M3 Local Deployment: 23B Active Parameters ≠ 23GB VRAM — A Complete Guide to MoE Architecture

MiniMax M3 is a 428B MoE model. Its 23B active parameters reflect per-token compute, not VRAM needs. Learn the MoE trade-offs, quantization options, and deployment paths to avoid the most common misconception.

Jul 19, 2026·2 min

Kimi K3 Leads the Charge: Inside the AI Coding Agent Framework Transparency Race

Kimi K3 sets a new open-weight record at 2.8T params, GrokBuild pivots to local-first after a privacy crisis, Open Interpreter rewrites in Rust — a deep dive into five major AI coding agent developments and the shift toward harness transparency.

Jul 19, 2026·7 min

OpenAI Loses Over $100 Billion a Year: How the AI Cost Paradox Is Devouring Tech Giants

Leaked financials show OpenAI's -122% operating margin — losing money on every sale. MIT research reveals 95% of enterprise AI investments yield zero returns. A deep dive into the AI cost paradox.