Ollama

Local deployment of LLMs has become increasingly popular as developers and organizations seek enhanced privacy, reduced latency, and greater control over their AI infrastructure.

The democratization of AI is here. With open-source LLMs like Llama 3, Mixtral, and Qwen now rivaling proprietary models, teams can build powerful AI infrastructure using consumer hardware - slashing costs while maintaining complete control over data privacy and deployment.

I dug up some interesting performance tests of GPT-OSS 120b running on Ollama across three different platforms: NVIDIA DGX Spark, Mac Studio, and RTX 4080. The GPT-OSS 120b model from the Ollama library weighs in at 65GB, which means it doesn’t fit into the 16GB VRAM of an RTX 4080 (or the newer RTX 5080).

Running large language models (LLMs) locally has become increasingly popular for privacy, cost control, and offline capabilities. The landscape shifted significantly in April 2025 when Docker introduced Docker Model Runner (DMR), its official solution for AI model deployment.

This guide provides a comprehensive overview of available Go SDKs for Ollama and compares their feature sets.

Here is a comparison between Qwen3:30b and GPT-OSS:20b focusing on instruction following and performance parameters, specs and speed:

In this post, we’ll explore two ways to connect your Python application to Ollama: 1. Via HTTP REST API; 2. Via the official Ollama Python library.

Ollama’s GPT-OSS models have recurring issues handling structured output, especially when used with frameworks like LangChain, OpenAI SDK, vllm, and others.

Large Language Models (LLMs) are powerful, but in production we rarely want free-form paragraphs. Instead, we want predictable data: attributes, facts, or structured objects you can feed into an app. That’s LLM Structured Output.

Here I am comparing how much VRAM new version of Ollama allocating for the model vs previous Ollama version. The new version is worse.

Ollama has quickly become one of the most popular tools for running LLMs locally. Its simple CLI, and streamlined model management have made it a go-to option for developers who want to work with AI models outside the cloud. But as with many promising platforms, there are already signs of Enshittification:

Locally hosted Ollama allows to run large language models on your own machine, but using it via command-line isn’t user-friendly. Here are several open-source projects provide ChatGPT-style interfaces that connect to a local Ollama.

Since standard Ollama doesn’t have a direct rerank API, you’ll need to implement reranking using Qwen3 Reranker in GO by generating embeddings for query-document pairs and scoring them.

In this test I’m comparing how different LLMs hosted on Ollama translate Hugo page in English to German. Three pages I tested were on different topics, had some nice markdown with some structure: headers, lists, tables, links, etc.

This little Reranking Go code example is calling Ollama to generate embeddings for the query and for eache candidate document, then sorting descending by cosine similarity.

The Qwen3 Embedding and Reranker models are the latest releases in the Qwen family, specifically designed for advanced text embedding, retrieval, and reranking tasks.