Archive - The Kaitchup – AI on a Budget

vLLM vs Ollama: How They Differ and When To Use Them

With Examples of Offline and Online Inference

Jul 7 •

The Weekly Kaitchup #99

IFBench - ERNIE 4.5 - Gemma 3n

Jul 4 •

June 2025

Gemma 3n: Fine-Tuning, Inference, and Submodel Extraction

Running Gemma 3n with vLLM and fine-tuning with TRL

Jun 30 •

The Weekly Kaitchup #98

Survey - Mistral 3.2 - And More News

Jun 27 •

Get the Best from GGUF Models: Optimize Your Inference Hyperparameters

The default hyperparameters are suboptimal for quantized models

Jun 23 •

The Weekly Kaitchup #97

Survey - Axolotl + LLM Compressor

Jun 20 •

RAG with Qwen3 Embedding and Qwen3 Reranker

How to use embedding and reranker models to efficiently retrieve only the most relevant chunks or documents given a user query

Jun 19 •

RTX 6000 Pro vs H100 & A100: Best Single-GPU Choice for Fast, Low-Cost LLM Fine-Tuning

Faster, cheaper single-GPU training

Jun 16 •

The Weekly Kaitchup #96

Magistral - Text-to-LoRA

Jun 13 •

Fine-Tuning 2-Bit Qwen3 Models on Your Computer

Code and best practices

Jun 9 •

The Weekly Kaitchup #95

Qwen3 Embeddings/Reranker - Packing Improved - Unsloth's Notebooks - SGLang vs. vLLM

Jun 6 •

Qwulu 3: Fine-Tuning Qwen3 Base with LoRA and TULU 3's Supervised Fine-Tuning Recipe

Can a supervised fine-tuning recipe that works effectively on Llama 3.1 be applied directly to Qwen3?

Jun 5 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts