Andrej Baranovskij Blog

In this video, I put Gemma 4 to the test on a real-world task — extracting structured data from bank statements — and benchmark it head-to-h...

In this video I show how to run multiple vLLM model instances on the same GPU (Nvidia) in parallel by adjusting the --gpu-memory-utilization...

I show you how to keep your vLLM model loaded in FastAPI cache for much faster inference — without reloading it on every request.   

I was running detail tests to compare accuracy for the same models (Qwen3-VL and Mistral Small 3.2) running on Ollama and MLX-VLM (recent 0....

MLX runs faster on first inference, but thanks to model caching or other optimizations by Ollama, second and next inference runs faster on O...

I added instruction and validation functionality into Sparrow. This allows to process business logic with document data directly through Spa...

I show how Sparrow can be used to handle complex Upwork task, with accurate table data extraction. Key requirement is to prevent Vision LLM ...

Discover how to fix number formatting errors in vision LLMs like Mistral! In this video, I show how Mistral misreads "56,000" as ...

I discuss the real-world MLX performance of Sparrow for structured data extraction with public access. The current Sparrow online instance r...

Learn how to streamline table data extraction with Sparrow, Table Transformer, Qwen2 VL, and MLX on the Mac Mini M4 Pro. Simplify your workf...

I show how to retrieve structured JSON output from table image using Qwen2-VL-7B. This VLLM performs OCR and data mapping tasks all out of t...