Local AI and Quantisation
Running models on your own hardware: VRAM budgets, GGUF and quantisation, Ollama and local routing.
- 1
Red Team vs. Green: Local AI Hardware Wars
NVIDIA's CUDA rules AI, leaving AMD users battling a "green wall." Explore the hardware wars and thorny paths forward.
- 2
Why Local AI Inference Is Beating the Cloud
AI supercomputers are landing on your desk! Discover why local AI is indispensable for enterprises facing API costs, latency, and privacy.
- 3
The Three Tribes of Local AI
Local AI: privacy, creativity, and compliance. Discover why keeping AI close to home is more than a trend.
- 4
Community Depth vs. Raw Power in Local AI
Is Stable Diffusion becoming a relic? Corn and Herman debate the rise of Flux, the privacy of local AI, and the future of open-source generation.
- 5
Why Agentic AI Needs More VRAM Than You Think
Learn how to build a high-performance local AI server for agentic coding, from dual-GPU PC builds to the power of Mac's unified memory.
- 6
Will Your Browser Replace Your OS for Local AI?
See how Web GPU and Web NN are turning your browser into a local AI engine, ending the era of complex DIY setups and protecting your privacy.
- 7
Why VRAM Is the Wrong Way to Measure Your AI PC
Forget VRAM—bandwidth is the new king. Discover why your local AI feels slow and how to build a true "agent computer" for professional coding.
- 8
From Ollama to Agentic CLIs: The Rise of the AI Harness
Explore the evolution from local LLMs to modern agentic CLIs, focusing on the "harness" that gives models context, tools, and autonomy.
- 9
Why Google's 31B Model Fits in Your GPU
Google just dropped Gemma four, and its 31-billion-parameter size is a masterclass in hardware-aware AI design.
- 10
Local AI vs Cloud AI: The Agent Identity Crisis
Your desktop is becoming a life support system for AI agents. We explore the sharp trade-offs between local-first and cloud-native architectures.
- 11
The Art of Squeezing AI Models onto Your GPU
Those cryptic letters on Hugging Face actually map how much brain power you trade for speed.
- 12
The "MPEG Moment" for AI: Llamafile & Native Models
Why are we squeezing massive cloud models onto desktops? Meet the "native" AI revolution.
- 13
MoE vs. Dense: The VRAM Nightmare
MoE models promise giant brains on a budget, but why are engineers fleeing back to dense transformers? The answer is memory.
- 14
Cloud-Local AI Hybrid: Does It Actually Work?
Can you pair Claude's reasoning with a local Qwen 7B for savings? The gap is wider than you think.
- 15
Video Tokens, Omni, and the Local VRAM Math
Video costs ~100 tokens per second. That single number explains why ChatGPT hides video upload and why local inference hits a KV cache wall.
- 16
Batch Inference on Your Own GPU: vLLM, SGLang, Ollama, llama.cpp
Hosted batch APIs sell you half-price tokens. Here's how to get the same file-in, file-out workflow on your own Linux box.
- 17
One Endpoint, Many Boxes: Local LLM Routing
A LiteLLM-style proxy can fail over between your own GPU boxes and the cloud — but it can't see your VRAM.
- 18
What 12GB of VRAM Can Actually Do Now
Local AI on a mid-range AMD card: what fits, what's fast, and what's still out of reach in 2026.