Availability, real-world retail pricing across six countries, and comparison against Mac Studio.
NVIDIA DGX Spark is real, on sale Oct 15, 2025, and targeted at CUDA developers needing local LLM work with an integrated NVIDIA AI stack. US MSRP $3,999; UK/DE/JP retail is higher due to VAT and channel. AUD/KRW public sticker prices are not yet widely posted.
Comparing Speed, parameters and performance of these two models
Here is a comparison between Qwen3:30b and GPT-OSS:20b focusing on instruction following and performance parameters, specs and speed:
+ Specific Examples Using Thinking LLMs
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.
Not very nice.
Ollama’s GPT-OSS models have recurring issues handling structured output, especially when used with frameworks like LangChain, OpenAI SDK, vllm, and others.
Slightly different APIs require special approach.
Here’s a side-by-side support comparison of structured output (getting reliable JSON back) across popular LLM providers, plus minimal Python examples
A couple of ways to get structured output from Ollama
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.
My own test of ollama model scheduling
Here I am comparing how much VRAM new version of Ollama allocating for the model vs previous Ollama version. The new version is worse.
My view on current state of Ollama development
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:
Quick overview of most prominent UIs for Ollama in 2025
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.
In july 2025, soon it should be available
Nvidia is about to release NVIDIA DGX Spark - little AI supercomputer on blackwell architecture with 128+GB unified RAM and 1 PFLOPS AI performance. Nice device to run LLMs.
Longread about MCP scpecs and implementation in GO
Here we have a description of The Model Context Protocol (MCP), short notes on how to implement an MCP server in Go, including message structure, protocol specifications.
Implementing RAG? Here are some Go code bits - 2...
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.
qwen3 8b, 14b and 30b, devstral 24b, mistral small 24b
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.
Implementing RAG? Here are some codesnippets in Golang..
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.
New awesome LLMs available in Ollama
The Qwen3 Embedding and Reranker models are the latest releases in the Qwen family, specifically designed for advanced text embedding, retrieval, and reranking tasks.
Thinking of installing second gpu for LLMs?
How PCIe Lanes Affect LLM Performance? Depending on the task. For training and multi-gpu inferrence - perdormance drop is significant.
