The Kaitchup – AI on a Budget

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

The Weekly Kaitchup #96

Fine-Tuning 2-Bit Qwen3 Models on Your Computer

The Weekly Kaitchup #95

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

Running DeepSeek-R1-0528 with a Single 24 GB GPU

The Weekly Kaitchup #94

Padding-Free vs. Packing: Fast and Efficient Fine-Tuning for LLMs Explained

Qwen3-30B-A3B vs Qwen3-32B: Is the MoE Model Really Worth It?

The Weekly Kaitchup #93

Qwen3: When <|im_end|> Suddenly Becomes <|endoftext|>

Boost 2-Bit LLM Accuracy with EoRA