Hardware

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).

Docker Model Runner (DMR) is Docker’s official solution for running AI models locally, introduced in April 2025. This cheatsheet provides a quick reference for all essential commands, configurations, and best practices.

In today’s computing landscape, virtualization has become essential for development, testing, and running multiple operating systems. For Linux users seeking a simple, intuitive way to manage virtual machines, GNOME Boxes stands out as a lightweight and user-friendly option that prioritizes ease of use without sacrificing functionality.

The future of AI is not only about smarter models. It is also about silicon that matches how those models are actually served. Specialized hardware for LLM inference is following a path reminiscent of Bitcoin mining’s move from GPUs to purpose-built ASICs, only with harder constraints because models and precision recipes keep evolving.

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.

Let’s compare prices for top-level consumer GPUs, that are suitable for LLMs in particular and AI in general. Specifically I’m looking at RTX-5080 and RTX-5090 prices. They have slightly dropped.

GPU load monitoring applications: nvidia-smi vs nvtop vs nvitop vs KDE plasma systemmonitor.

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.

Let’s compare prices for top-level consumer GPUs, that are suitable for LLMs in particular and AI overall. Specifically have a look at RTX 5080 and RTX 5090 prices. They have slighty dropped.

Just 3 month ago we didn’t see RTX 5090 in shops, and now here they are, but the prices are slightly higher then MRSP. Let’s compare the cheapest prices for RTX 5080 and RTX 5090 in Australia and see how it goes.

Top Automated system for some awesome job.

How PCIe Lanes Affect LLM Performance? Depending on the task. For training and multi-gpu inferrence - perdormance drop is significant.

I was hit hard by this issue. But you should investigate and test your PC if your BSOD is like mine. The cause was Intel’s CPU Degradation Issue in 13th and 14th generation.

I’ve got a theory to test - if utilising ALL cores on Intel CPU would raise the speed of LLMs? This is bugging me that new gemma3 27 bit model (gemma3:27b, 17GB on ollama) is not fitting into 16GB VRAM of my GPU, and partially running on CPU.

In the midst of the modern world’s turmoil here I’m comparing tech specs of different cards suitable for AI tasks (Deep Learning, Object Detection and LLMs). They are all incredibly expensive though.

This guide explains how Ollama handles parallel requests (concurrency, queuing, and resource limits), and how to tune it using the OLLAMA_NUM_PARALLEL environment variable (and related knobs).