Tag

#ollama

519 posts15 followers

Explore Hashnode

Alternatives

Mayank Rajput3d ago · 3 min read

What broke when we ran an AI coding agent on local Ollama models (including a 4GB GPU)

We build an AI app builder, and one feature we wanted was "bring your own Ollama": point the agent at your own models and pay nothing for tokens. Getting a chat answer out of a local model is easy. Ge

nocoder.hashnode.dev

Amaresh Pelleti5d ago · 10 min read

Ollama Docker Setup: GPU, Volumes and Compose

Originally published on DevToolHub. Running Ollama in a container takes one docker run command. That command also decides two things the docs bury: whether your models survive a rebuild, and whether

devtoolhub.hashnode.dev

Oleg Che5d ago · 7 min read

A one-click local LLM installer for Windows: Python, pywebview, Ollama and hardware-based model picking

Running a local LLM is easy to do once and annoying to explain: install Ollama, work out which model fits your GPU, get the tag right, wait for gigabytes, find a UI. People kept asking me to set this

olegche.hashnode.dev

Frederick Wong Sin Hin5d ago · 6 min read

Shipped: A Second Brain That Makes the First One Cheaper

Originally published on ecupse.com. We spent 5,595 Kiro credits last month. The trend line is not flat. I know this because I built the dashboard that tracks it. Every week, a pipeline mines our real

ecupse.hashnode.dev

Andolasoft Inc6d ago · 2 min read

Air-Gapped AI Analytics: Apache Superset with Local LLMs (Ollama and vLLM)

Somebody senior has seen a demo. A business user types “which branches had the worst collection efficiency last quarter” and a chart appears. Now they want it in your bank, your ministry or your hospi

andolasoft.hashnode.dev

IshantKaushikNov 1 · 3 min read

I built a small engine that gives local LLMs real tools

Small local models are good at chatting and bad at the basics. They get math wrong, they forget everything between chats, and when they don't know something they make it up. I got tired of that, so I

local-ai-notes.hashnode.dev

Agent Infra GuideNov 1 · 4 min read

Why Tokens per Second Isn't Enough to Evaluate a Local LLM

Disclosure: I represent Agent Infra Guide, which publishes the benchmark collection linked below. It's tempting to compare local language models using one number: tokens per second. But a model that g

1 agentinfraguide.hashnode.dev

AIHostBoxOct 29 · 6 min read

Run Open WebUI with Ollama on a small VPS (CPU only)

Most Open WebUI tutorials assume you have a GPU on your desk. Plenty of people don't. They have a 4 GB or 8 GB VPS and want a private chat UI with a small local model, plus maybe an API key for the he

aihostbox.hashnode.dev

Raghul MOct 27 · 11 min read

From Old Drives to Pocket AI: Building a Portable Local LLM Router

How I repurposed an old pendrive and external hard disk to store local AI models, offload storage from my MacBook, and build a decision-model-powered router that sends prompts to specialized LLMs. The

2 blog.raghul.in

Ankit KumarOct 28 · 15 min read

The best local LLMs for coding in 2026, and the hardware each one needs

tldr: If you have 16 GB of memory, run gpt-oss-20b. On 24 to 32 GB, run Qwen3.8-27B, the best local coding model in 2026, and keep Muse Glimmer-30B as the runner-up. Both are Apache 2.0. With 80 GB or

hashnode.com

Search Hashnode