Local & Open-Weight Models
Deployment-focused content for open-weight models — running Gemma, Qwen, etc. locally, on phones, laptops, edge devices. Setup guides, hardware requirements, deployment patterns. Single-model reviews and explainers go under AI Model Reviews & Comparisons instead.
DeepSeek's 'Thinking with Visual Primitives': 5 Technical Breakthroughs in the Paper That Briefly Disappeared
DeepSeek's vision paper was published then pulled. Here are 5 key technical details — including inline bounding-box tokens and a 7,000x compression ratio.
DeepSeek V4 Flash vs Claude Sonnet 4.6: Which Model Is Best for AI Agent Workflows?
Compare DeepSeek V4 Flash and Claude Sonnet 4.6 on cost, speed, and quality for agentic coding, automation, and multi-step workflows.
DeepSeek Vision's 7,000x Image Compression Pipeline: From 756px Input to 81 KV Cache Entries
DeepSeek's vision model compresses a 756x756 image through four stages down to 81 KV cache entries — a ~7,000x total compression ratio. Here's each step.
DeepSeek Vision Beats GPT-5.4 by 17 Points on Maze Navigation — The Topological Reasoning Benchmark Explained
On maze navigation, DeepSeek's vision model scores 67% vs. GPT-5.4's 50% — a 17-point gap driven by inline bounding-box spatial reasoning.
DeepSeek Vision vs. Claude Sonnet 4.6 vs. Gemini Flash 3: Which Vision Model Uses 10x Less KV Cache?
DeepSeek's vision model uses ~90 KV cache entries per image vs. ~870 for Sonnet 4.6 and ~1,000 for Gemini Flash 3. Here's what that means for cost.
How to Use Free Claude Code Alternatives: OpenRouter, NVIDIA NIM, and Ollama Setup Guide
Run Claude Code with DeepSeek, GLM, or Gemma models via OpenRouter, NVIDIA NIM, or Ollama to cut costs by up to 99% with the free-claude-code proxy.
What Is the Mistral Medium 3.5 Model? Open-Weight AI Built for Agent Harnesses
Mistral Medium 3.5 is a 128B open-weight model combining reasoning, coding, and instruction-following for agent harnesses like OpenClaw and Hermes.
How to Build a Local AI Stack from Scratch: Ollama to vLLM, Step by Step
From Ollama for daily use to vLLM for serving to TensorRT-LLM for production — here's the complete local AI runtime stack and when to use each layer.
DeepSeek V4 Launch: 5 Specs That Threaten Closed Frontier Labs
DeepSeek V4 dropped with 1M token context, open weights, and pricing that undercuts GPT-5.5 by nearly 9x on output tokens.
DeepSeek V4 Vision: 10x Cheaper Multimodal AI for Your Workflows
DeepSeek V4's vision model uses 90 KV cache entries vs 870 for Claude—10x cheaper. Learn how to use it in your AI workflows and agents.
DeepSeek V4 Vision Model: 10x KV-Cache Efficiency and 67% Maze Navigation vs GPT-5.4's 50%
DeepSeek's vision variant uses ~90 KV-cache entries per image vs Claude Sonnet 4.6's ~870 — and beats GPT-5.4 on maze navigation 67% to 50%.
Mac Mini M4 Pro vs RTX 5090 vs DGX Spark: Which Local AI Hardware Is Right for You in 2026?
Mac mini M4 Pro at 64GB, RTX 5090 at 32GB GDDR7, or DGX Spark at 128GB unified memory — here's the honest hardware comparison for running AI models locally.
How to Use NVIDIA NIM Free Models in Your AI Workflows
NVIDIA NIM offers free models like GLM 4.7 via API. Learn how to connect them to Claude Code or any agentic tool to reduce costs without sacrificing capability.
How to Use Ollama to Run AI Models Locally for Claude Code Workflows
Ollama lets you run models like Gemma 4 locally on your own hardware—zero API costs. Learn how to connect it to Claude Code as a free backend alternative.
How to Run Claude Code Against DeepSeek V4 for $3 a Session (Step-by-Step)
The free-cloud-code GitHub proxy lets you use the full Claude Code CLI with DeepSeek backends. Here's the exact setup to cut your AI coding costs.
What Is Visual Primitives Reasoning? DeepSeek's Breakthrough for AI Agents
DeepSeek's 'thinking with visual primitives' lets AI agents point to objects during reasoning—solving the reference gap that breaks multimodal tasks.
How to Run Claude Code with Cheaper Models: OpenRouter, NVIDIA NIM, and Ollama
Use Claude Code's interface with DeepSeek, Gemma, and other affordable models via proxy. Get 80–90% of Opus quality at 2–5% of the cost.
DeepSeek V4 vs Claude Opus 4.7: Which Model Is Right for Your AI Workflows?
Compare DeepSeek V4 and Claude Opus 4.7 on benchmarks, pricing, context length, and agentic use cases to find the best model for your stack.
Local AI vs Cloud AI: How to Decide What to Own and What to Rent
Not all AI work belongs in the cloud. Learn how to route tasks between local models and cloud APIs based on privacy, cost, and context requirements.
How to Use Ollama to Run AI Models Locally: A Beginner's Setup Guide
Ollama lets you run open-weight models like Gemma 4 and Llama locally on your own hardware. Here's how to get started with local AI inference in minutes.
What Is DeepSeek V4? Open-Weight AI at Frontier-Level Performance
DeepSeek V4 is an open-source model with a 1M token context window that rivals closed frontier models at a fraction of the cost. Here's what you need to know.
The 7-Model Local AI Portfolio: How to Route Tasks Across Local and Cloud Models for Maximum Performance
One model can't do everything. Here's the 7-model local portfolio — from fast local inference to frontier cloud fallback — and how to route between them.
DeepSeek V4 Launch: 4 Specs That Make It the Most Disruptive Open-Weight Model of 2026
Open-weight, 1M token context, $1.74/M tokens, near-frontier benchmarks. DeepSeek V4's four headline numbers and what they mean for enterprise AI.
DeepSeek V4 vs GPT-5.5 vs Claude Opus 4.7: Is 3x Cheaper Worth the Benchmark Trade-Off?
DeepSeek V4 costs $1.74/M tokens vs $5/M for GPT-5.5 and Opus 4.7. We break down where benchmark parity holds and where it doesn't.