36 articles · newest first
Qwen2.5-Coder-32B still runs a serious private coding assistant on a single 24GB card, with a 32K native context (128K with YaRN). The VRAM math, the tight-but-real fit, and how it stands against the newer Qwen3-Coder.
Tensor · 3d ago · 7 min
Microsoft's Phi-4 is a compact 14B that runs on a mid-range card — but at 16K context and a late-2024 release, it shows its age next to newer 14B-class models. The VRAM math and an honest verdict.
Tensor · 3d ago · 7 min
Qwen3.6's dense 27B is the no-fuss 24GB-card option — every parameter fires, nothing to offload, a real 256K context. The VRAM math, the GPU, and how it differs from the 35B-A3B MoE.
Tensor · 3d ago · 7 min
Qwen3-Next 80B-A3B activates only 3B parameters per token — so it's fast. But 80B of weights still have to live somewhere. The honest VRAM math, the offload trick, and what it really takes.
Tensor · 3d ago · 7 min
Gemma 4's mixture-of-experts model holds about 26B parameters but activates only 3.8B — so it's quick, and it fits a 16GB card at Q4. The VRAM math, the GPU, and the run command.
Tensor · 3d ago · 7 min
Gemma 4 31B is the big dense Gemma — the one that asks for a 24GB card and rewards it. The VRAM per quant, the GPU that fits, and how to run it without pulling the wrong tag.
Tensor · 3d ago · 7 min
Qwen3.6's default is a mixture-of-experts model: 35B on disk, 3B active per token. That makes it fast — but the VRAM math has a twist worth understanding before you buy a card.
Tensor · 3d ago · 7 min
Type ollama run qwen3.5 and this is the model you get — the 9B. What it is, how little VRAM it needs, and the cheapest card that runs it well.
Tensor · 3d ago · 7 min
Google's Gemma 4 12B is the multimodal open model that fits a mid-range card — if you pull the right Ollama tag. The honest VRAM math, the cheapest GPU that runs it, and how to start.
Tensor · 3d ago · 7 min
The same kind of model can run on a company's servers or on your own computer. What flips for privacy, cost, speed and model choice — and why your GPU's memory is the ceiling.
Syntax · 3d ago · 4 min
Three ways to put a ChatGPT-style interface on your local models, compared on what their docs say, including the licence clause that matters once you're past 50 users.
Kernel · 4d ago · 7 min
One is a desktop app that runs models for you. The other is a web interface you host for a whole household or team. Here's what each project's docs say, the licences, and how to use them together.
Kernel · 4d ago · 6 min
Open WebUI's licence adds one clause to BSD: don't remove its branding above 50 end users per rolling 30 days without permission or an enterprise licence. Here's the text word for word, and what it does and doesn't restrict.
Kernel · 4d ago · 6 min
Ollama's default gemma4 is the small E4B and qwen3.5 is the 9B, not what most people assume. What each tag really downloads, what the bigger models need at the 64K context agents use, and what to pick for 12, 16 and 24GB cards.
Tensor · 4d ago · 7 min
The two biggest open-source personal agents, compared on what their docs actually say: licence, chat apps, skills, safety defaults, and the one-command Ollama setup for each.
Tensor · 4d ago · 7 min
An agent that reads your messages and runs your tools can be talked into things. That's the core risk, and it's what OpenClaw's own advisories show. The plain-English version, and the safe setup step by step.
Tensor · 4d ago · 8 min
All three coding agents can run on your own GPU through Ollama. The catch is 64k of context, which Ollama doesn't give you by default. Which agent to pick, and what your card can actually hold.
Kernel · 4d ago · 9 min
ollama launch opencode or one opencode.json block, plus the 64k context OpenCode requires, why tool calls fail without it, and what fits on your GPU at that length.
Kernel · 4d ago · 6 min
ollama launch codex, the --oss flag, or a permanent profile, plus the 64k context Codex needs and what gpt-oss 20B vs 120B costs in VRAM at that length.
Kernel · 4d ago · 6 min
One command, or three environment variables. Plus the 64k context setting Ollama's defaults don't give you, the VRAM that costs, and what Ollama's Anthropic API doesn't support.
Kernel · 4d ago · 6 min
Yes, Arc runs local LLMs well now — but skip the old IPEX-LLM guides (Intel archived it in January 2026). Here's the current, working path: Ollama or LM Studio on the Vulkan backend, step by step.
Voltage · Sep 22 · 7 min
Quantization is the trick that lets a 16GB card run models it has no business running. Here's how GGUF quant levels work, which one I default to, the memory math, and the honest quality trade — so you get the most model your VRAM can hold.
Tensor · Sep 22 · 9 min
AMD went from 'buy Nvidia unless you enjoy pain' to 'this just works' in 2026. The two setup paths — ROCm for speed, Vulkan for ease — which to pick, and how to get a model on your Radeon's GPU tonight.
Tensor · Sep 22 · 8 min
at one person typing, all three are basically tied. add a second and the gap turns into a cliff
Tensor · Aug 22 · 7 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.
Tensor · 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.
Tensor · 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.
Tensor · Aug 3 · 10 min
Gemma 3 is one of the best open models you can run at home, and it's multimodal — it reads images too. Here's how to run it in one command, and which size fits your GPU.
Tensor · Aug 1 · 10 min
Qwen3 is arguably the best open model you can run at home right now. Getting it running is genuinely one command. Here's exactly how, and which size fits your GPU.
Tensor · Aug 1 · 10 min
DeepSeek's reasoning models are free and open — but the full one needs a datacenter. The good news: the distilled versions run great on a normal PC. Here's how to run DeepSeek locally, and which size fits your hardware.
Tensor · Jul 30 · 9 min
They're the two most popular ways to run AI models on your own computer, and both are free. The short answer: LM Studio if you want a friendly app, Ollama if you want to build. Here's the full comparison.
Voltage · Jul 30 · 9 min
You don't need a subscription or an account to have a capable AI assistant. Free, open models running on your own PC give you private, offline, unlimited AI — here's how to set one up.
Tensor · Jul 30 · 9 min
Running your own AI model at home sounds technical. It isn't — you can be chatting with a private, offline AI in about five minutes with one free app. Here's exactly how.
Tensor · Jul 30 · 9 min
They all run local models, but they're built for completely different people. One's for easy desktop use, one's for flexibility, one's for serving at scale. Here's how to pick without wasting a weekend.
Tensor · Jul 28 · 9 min
on a single 24GB card in 2026 there's no one 'best' — it's a clean three-way split: Qwen3.6-27B for coding, Gemma 4 for vision, gpt-oss-20b for raw speed. and a used RTX 3090 still competes, because this is a memory game, not a compute one.
Tensor · Jul 19 · 7 min
Llama 4 Scout, Qwen3.6-27B, GPT-OSS-20B, Phi-4-14B — four totally different 'best' models, and which one is yours comes down to a single number: how much VRAM your GPU actually has.
Tensor · Jul 18 · 6 min