[{"data":1,"prerenderedAt":46},["ShallowReactive",2],{"blog-post-use-ollama-from-anywhere":3,"blog-index":16},{"slug":4,"title":5,"excerpt":6,"author":7,"authorBio":8,"publishedAt":9,"readMinutes":10,"tags":11,"coverImage":14,"body":15},"use-ollama-from-anywhere","Use Ollama from anywhere, in three steps","Reach the models on your home GPU from a laptop, a CI job or a teammate's machine, without opening a single port or setting up a VPN.","The Tokmine team","We build Tokmine, a traffic manager for local AI models.","2026-09-22T09:00:00.000Z",4,[12,13],"Ollama","Tutorial","\u002Fblog\u002Fuse-ollama-from-anywhere.svg","\n      \u003Cp class=\"lead\">You have Ollama on a machine with a good GPU. Here is how to use it from anywhere.\u003C\u002Fp>\n\n      \u003Ch2>1. Install the CLI\u003C\u002Fh2>\n      \u003Cpre>\u003Ccode>curl -fsSL https:\u002F\u002Ftokmine.ai\u002Finstall.sh | sh\u003C\u002Fcode>\u003C\u002Fpre>\n      \u003Cp>On Windows, use \u003Ccode>irm https:\u002F\u002Ftokmine.ai\u002Finstall.ps1 | iex\u003C\u002Fcode>.\u003C\u002Fp>\n\n      \u003Ch2>2. Run it\u003C\u002Fh2>\n      \u003Cpre>\u003Ccode>tokmine\u003C\u002Fcode>\u003C\u002Fpre>\n      \u003Cp>The CLI finds Ollama on port 11434, detects that it speaks both the Ollama and OpenAI dialects, and prints a public URL such as \u003Ccode>https:\u002F\u002Ftunnel.tokmine.ai\u002Ft\u002F<slug>\u003C\u002Fcode> with a token. Without an account this lasts 30 minutes.\u003C\u002Fp>\n\n      \u003Ch2>3. Point your client at it\u003C\u002Fh2>\n      \u003Cpre>\u003Ccode>from openai import OpenAI\n\nclient = OpenAI(\n    base_url=\"https:\u002F\u002Ftunnel.tokmine.ai\u002Ft\u002F<slug>\u002Fv1\",\n    api_key=\"<token>\",\n)\nclient.chat.completions.create(\n    model=\"llama3.2\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello\"}],\n)\u003C\u002Fcode>\u003C\u002Fpre>\n\n      \u003Ch2>Keeping it\u003C\u002Fh2>\n      \u003Cp>Create an account and run \u003Ccode>tokmine login\u003C\u002Fcode> to keep the machine online permanently. It costs $0.50 per machine per month, plus $0.50 per person who calls it. Read more in the \u003Ca href=\"\u002Fdocs\u002Fapi-compat\">API compatibility docs\u003C\u002Fa>.\u003C\u002Fp>\n    ",[17,26,36,38],{"slug":18,"title":19,"excerpt":20,"author":7,"authorBio":8,"publishedAt":21,"readMinutes":10,"tags":22,"coverImage":25},"one-token-per-teammate","One token per teammate: share a local model safely","Passing around one API key works until it leaks or someone runs a job all night. Per-user tokens make a shared model safe to hand out.","2026-09-30T09:00:00.000Z",[23,24],"Teams","Security","\u002Fblog\u002Fone-token-per-teammate.svg",{"slug":27,"title":28,"excerpt":29,"author":7,"authorBio":8,"publishedAt":30,"readMinutes":31,"tags":32,"coverImage":35},"local-vs-hosted-ai-cost","Local or hosted AI? What running your own models costs","Hosted APIs bill per token. Local models bill in hardware, power and your time. Here is how to compare the two without fooling yourself.","2026-09-29T09:00:00.000Z",5,[33,34],"Cost","Local models","\u002Fblog\u002Flocal-vs-hosted-ai-cost.svg",{"slug":4,"title":5,"excerpt":6,"author":7,"authorBio":8,"publishedAt":9,"readMinutes":10,"tags":37,"coverImage":14},[12,13],{"slug":39,"title":40,"excerpt":41,"author":7,"authorBio":8,"publishedAt":42,"readMinutes":31,"tags":43,"coverImage":45},"why-local-models-need-a-traffic-manager","Why local AI models need a traffic manager","One GPU box is a hobby. Three machines and five teammates is a routing problem. Here is what changes when your models live on your own hardware.","2026-09-15T09:00:00.000Z",[34,44],"Architecture","\u002Fblog\u002Fwhy-local-models-need-a-traffic-manager.svg",1790768272351]