Category: computers
-
AI@Home – DeepSeek R1 8B
Conditions & context Today we are poking needles into DeepSeek R1 8B AI model, specifically the 0528 update, which is based on Qwen3 8B model. Since I have an 16GB card I’ve picked the 8-bit variant. Spoiler alert! This model would give Dostoyevsky and Tolstoy run for their money! :-) As in all my tests,…
-
AI@Home – Mistral Nemo 12B
Conditions & context Today we’re looking at Mistral Nemo 12B model with 5-bit quantization and if my great experience of their 4B model was any indication, this 3-times-larger model with 12 billion parameters is looking up! Let’s dive in! As in all my tests, I use the same prompt, the same hardware, and the same…
-
AI@Home – Gemma 3 12B
Conditions & context Today we are diving into a quick test of Google’s Gemma3, again a QAT quantized model, but this time a 12B. So, let’s hope that those 12 billion parameters do a better job than that “crazy” 4B sibling’s weights were. Let’s dive right in! As in all my tests, I use the…
-
AI@Home – Llama 3.1 8B Spits Fast
Conditions & context Today I’m looking at an AI model of Meta’s Llama 3.1 8B. Specifically its 5-bit quantized variant. So, let’s see how it compares to its equivalent — Mistral 7B. These are lightweight models, which should easily fit on a decent half-a-decade-old GPU. Let’s dive in! As in all my tests, I use…
-
AI@Home – Gemma3 4B
Conditions & context Today we are looking at Google’s Gemma3 4B IT QAT model, which is lightweight and looks promising. Do promises get delivered? Let’s dive in… As in all my tests, I use the same prompt, the same hardware, and the same methodology. I’m looking at the same set of metrics across every model:…
-
AI@Home – GPT OSS 20B
Conditions and context Here is my brief test of OpenAI’s free model GPT-OSS with 20 billion weight. Read on and judge for yourself whether this model is worth your time. Skip to the conclusion if you’re a TL;DR type. As in all my tests, I use the same prompt, the same hardware, and the same…
-
AI@Home – Gemma3 27B IT QAT
Conditions and context Today I’m looking at Gemma3 27B IT QAT model, or more precisely Gemma3 27-Billion-Prompt Instruction-Tuned Quantization-Aware Training. What a mouthful. A hefty 54GB model and my tested variant was just shy of 20GB. Before we dive any deeper, first the usual disclaimer: As in all my tests, I use the same prompt,…
-
AI@Home – Mistral 7B
Conditions & context Today we are looking at a lightweight French model, Mistral 7B Instruct. I chose the Q5 quantization version, thinking that the jump in VRAM utilization would be outweighed by increased accuracy. I’ve heard good things about it and it certainly looked promising. How was it? Let’s dive in… As in all my…
-
AI@Home – Qwen3 14B – Good Allrounder
Model Conditions & Context Here are the results of my brief test of Qwen3 14B AI model on a PC with the below specifications. Read on and you be the judge whether you think this AI model is worth your time and interest. Skip down to conclusion, if you are one of the TL;DR types.…