40 articles · newest first
Claude burned through 650 dead ends to push the Riemann zeta problem forward — real progress, not the proof half the internet is calling it.
Lena Fischer · 5d ago · 6 min
Muse Glimmer runs on a single consumer GPU and, per Meta's own numbers, beats Gemma4-31B and Qwen3.6-27B at agentic and coding tasks — and Zuckerberg used the release to make his most pointed case yet for open AI over the API-gated kind.
Lena Fischer · Aug 10 · 7 min
You don't need an expensive card for local reasoning. The cheap RTX 3060 12GB runs DeepSeek R1's 8B distill — genuine step-by-step thinking for around $200. Here's how, and the limits.
Lena Fischer · Aug 5 · 10 min
You keep seeing 'R1 distill 8B/14B/32B' — but what does 'distilled' mean, and why is a small distill so good at reasoning? Here's the plain-English explanation.
Lena Fischer · Aug 5 · 10 min
The 70B is bigger, but the 32B fits a single 24GB card and is faster. For most home setups the smaller distill is actually the smarter choice. Here's the honest comparison.
Lena Fischer · Aug 5 · 10 min
DeepSeek R1 comes in six distilled sizes, from 1.5B to 70B. Here's exactly which one fits your VRAM — and why the 32B on a 24GB card is the value sweet spot.
Lena Fischer · Aug 5 · 10 min
DeepSeek R1 is the best open model for step-by-step reasoning — and thanks to its distilled versions, you don't need a data center to run it. Here's whether it's worth it, and which version to run.
Lena Fischer · Aug 5 · 10 min
OpenAI's gpt-oss-20b is one of the best models you can run locally, and the cheapest new 16GB card handles it — full context included. Here's how, and what to expect.
Lena Fischer · Aug 5 · 10 min
One is free, private, and offline; the other is polished, cloud-hosted, and $10-19 a month. Here's the honest trade-off between a local Qwen3-Coder setup and GitHub Copilot.
Lena Fischer · Aug 5 · 10 min
Serve the model with Ollama or LM Studio, connect Continue or Cline, and you've got a local AI coding assistant inside VS Code — no subscription, no code leaving your machine.
Lena Fischer · Aug 5 · 10 min
From an 8GB laptop card to a 24GB desktop, here's exactly which Qwen3-Coder you can run — and why 24GB is the sweet spot for a genuinely good local coding assistant.
Lena Fischer · Aug 5 · 10 min
Qwen3-Coder is the model that finally makes a local, private coding assistant genuinely good. It tops the open-source coding benchmarks and runs on a 24GB card. Here's whether it's worth it.
Lena Fischer · Aug 5 · 10 min
Three of the best open models, three different strengths. gpt-oss is the cost-effective all-rounder, Qwen3 owns coding, DeepSeek owns hard reasoning. Here's how to pick for your work.
Lena Fischer · Aug 4 · 10 min
One fits on a gaming GPU; the other needs a data-center card. They're aimed at completely different people. Here's how to pick the right gpt-oss for your hardware and your goals.
Lena Fischer · Aug 4 · 10 min
OpenAI's gpt-oss-20b fits on a 16GB graphics card and flies at 225 tokens/second on an RTX 4090. But there's a context-length trap that quietly eats your VRAM — here's what you actually need.
Lena Fischer · Aug 4 · 10 min
OpenAI finally shipped open-weight models — gpt-oss-20b and gpt-oss-120b. The 20B runs on a 16GB card, the 120B rivals DeepSeek at a fraction of the cost. Here's whether they're worth running.
Lena Fischer · Aug 4 · 10 min
A common worry before going local: will my power bill explode? The honest answer is no for how most people use it — but here are the real numbers so you can decide for yourself.
Lena Fischer · Aug 4 · 10 min
You don't need a discrete graphics card to get GPU-accelerated local AI. A modern AMD Radeon iGPU shares your system RAM as VRAM and runs 7B models faster than a CPU — here's what to expect.
Lena Fischer · Aug 4 · 10 min
Every model comes in a dozen quant sizes and it's paralyzing. Here's the simple truth: Q4_K_M is the default for almost everyone, and here's exactly when to go higher.
Lena Fischer · Aug 4 · 10 min
You don't need a graphics card to run a local AI. A modern CPU with enough RAM runs small models fine — just slowly. Here's what's realistic, which models to pick, and when you really do need a GPU.
Lena Fischer · Aug 4 · 10 min
Local models pile up fast and each one is gigabytes. Here's the handful of Ollama commands to list, update, remove, and inspect your models — and keep your disk under control.
Lena Fischer · Aug 3 · 10 min
A '30B' model that runs as fast as a 3B one? That's a Mixture-of-Experts model, and it changes the local-AI math. Here's what MoE means and why it matters for what you can run.
Lena Fischer · Aug 3 · 10 min
For math, logic, and step-by-step problems, 'reasoning' models that think out loud beat regular chatbots. Here's the best one to run locally, from an 8GB card to a 24GB rig.
Lena Fischer · Aug 3 · 10 min
Yes, you can run a real language model on a Raspberry Pi 5. It won't be fast, but for a tiny, private, always-on AI it's genuinely fun and useful. Here's how, and what to expect.
Lena Fischer · Aug 3 · 10 min
A vector database stores the searchable version of your documents. For local RAG, the right one is simpler than the enterprise options everyone benchmarks. Here's what to actually use.
Lena Fischer · Aug 3 · 10 min
Embeddings are what let a local AI search your documents. Pick the wrong one and retrieval is bad; pick the right one and RAG just works. Here's the best local embedding model, by need.
Lena Fischer · Aug 3 · 10 min
Running your local AI stack in Docker keeps it isolated, portable, and easy to reset. It's the tidy way to run Ollama and a web UI together. Here's the simple setup.
Lena Fischer · Aug 3 · 10 min
Those sliders in your local AI app aren't decoration. Temperature and top-p control how creative or focused the model is — and getting them right transforms your results. Explained simply.
Lena Fischer · Aug 3 · 10 min
Local models can be run 'uncensored' — without the refusals and lectures of cloud chatbots. Here's how it works, the legitimate reasons to want it, and how to do it responsibly.
Lena Fischer · Aug 3 · 10 min
Point your editor at a model on your own machine and get autocomplete, chat, and even an agent that edits files — free, unlimited, and with your code never leaving your PC. Here's the setup.
Lena Fischer · Aug 3 · 10 min
A local vision model reads images, describes photos, and pulls text out of screenshots — all offline. Some open ones now beat GPT-4o at OCR. Here's how to run one, in one command.
Lena Fischer · Aug 3 · 10 min
For fiction, worldbuilding, and character roleplay, the best models are community fine-tunes that write like a collaborator, not a chatbot — and they run privately on your own machine.
Lena Fischer · Aug 3 · 10 min
An AI agent that uses tools and completes multi-step tasks, running offline with zero API fees. The stack is simpler than you'd think: Ollama plus a framework like CrewAI. Here's how.
Lena Fischer · Aug 3 · 10 min
Llama is the open model that kicked off the whole local-AI movement, and running it yourself is genuinely one command. Here's how, and which size fits your GPU.
Lena Fischer · Aug 3 · 10 min
AI doesn't read words — it reads tokens. They're why API pricing, context limits, and speed are all measured the way they are. Here's what a token actually is, in plain English.
Lena Fischer · Aug 3 · 10 min
The context window is how much text an AI can consider at once — your prompt, the conversation, and any documents. It's why chats 'forget', and why long context eats VRAM. Explained simply.
Lena Fischer · Aug 3 · 10 min
Local TTS has gotten shockingly good. You can generate natural narration for free on any PC, or clone a voice from a 6-second clip — all offline. Here's what to use.
Lena Fischer · Aug 3 · 10 min
OpenAI released open-weight models you can run yourself. The 20B fits a 16GB card thanks to clever quantization; the 120B needs a serious rig. Here's how to run gpt-oss locally.
Lena Fischer · Aug 3 · 10 min
Mistral's models are famously efficient — they punch above their size, so you get a lot on modest hardware. Here's how to run Mistral locally in one command, by size.
Lena Fischer · Aug 3 · 10 min
Point your apps, scripts, and coding tools at a model on your own machine instead of a paid cloud API. It's an OpenAI-compatible endpoint, it's free, and it's one command to start.
Lena Fischer · Aug 1 · 10 min