Series

Local AI and Quantisation

Running models on your own hardware: VRAM budgets, GGUF and quantisation, Ollama and local routing.

18 episodes
  1. 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.

    22:53 · 8 Dec 2025
  2. 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.

    21:18 · 9 Dec 2025
  3. 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.

    24:04 · 9 Dec 2025
  4. 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.

    24:53 · 23 Dec 2025
  5. 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.

    21:13 · 27 Dec 2025
  6. 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.

    26:33 · 9 Mar 2026
  7. 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.

    21:36 · 27 Mar 2026
  8. 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.

    24:53 · 29 Mar 2026
  9. 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.

    28:35 · 3 Apr 2026
  10. 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.

    28:39 · 4 Apr 2026
  11. 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.

    21:15 · 4 Apr 2026
  12. 12

    The "MPEG Moment" for AI: Llamafile & Native Models

    Why are we squeezing massive cloud models onto desktops? Meet the "native" AI revolution.

    22:39 · 5 Apr 2026
  13. 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.

    24:18 · 6 Apr 2026
  14. 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.

    26:10 · 24 Aug 2026
  15. 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.

    20:55 · 12 Oct 2026
  16. 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.

    21:12 · 15 Oct 2026
  17. 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.

    19:27 · 21 Oct 2026
  18. 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.

    22:31 · 23 Oct 2026