The Kaitchup – AI on a Budget

The Kaitchup – AI on a Budget

Home
Notes
AI Notebooks
The Kaitchup's Book
Weekly Kaitchup
Tutorials
The Kaitchup Index
Archive
About

OpenAI GPT-OSS: Native 4-Bit MoE Models

Everything you need to know about GPT-OSS 20B and 120B, MXFP4 quantization, and running on Blackwell & H100 GPUs -- The Weekly Kaitchup #104 Special Edition
READ THE LATEST
The Kaitchup – AI on a Budget
The Kaitchup – AI on a Budget
Weekly tutorials, tips, and news on fine-tuning, running, and serving large language models on your computer. The Kaitchup also proposes a collection of 160+ AI notebooks regularly updated.

Recent posts

View all
GSPO vs GRPO: Reinforcement Learning for MoE Models
How Qwen’s GSPO Outperforms GRPO for Stable and Scalable MoE Training
 • 
Benjamin Marie
The Weekly Kaitchup #103
Qwen3-2507 - DailyBench - Gemma 3 QAT Evaluation
 • 
Benjamin Marie
H100 PCIe vs SXM vs NVL: Which H100 GPU Is Fastest and Most Cost-Effective for Fine-Tuning LLMs?
Benchmarking all three H100 variants for full, LoRA, and QLoRA fine-tuning
 • 
Benjamin Marie
The Weekly Kaitchup #102
Qwen3’s “Dehybridization” - Qwen3-Coder - The Kaitchup Index
 • 
Benjamin Marie
1
Kimi K2: 1 T‑Param DeepSeek‑Inspired MoE, Re‑engineered & Trained from Scratch
Still expecting Llama 4 Behemoth? Check Kimi K2.
 • 
Benjamin Marie
The Weekly Kaitchup #101
QuTLASS - Voxtral - RAT
 • 
Benjamin Marie
Top posts
RAG with Qwen3 Embedding and Qwen3 Reranker
 • Benjamin Marie
4
LoRA Adapters: When a Naive Merge Leads to Poor Performance
 • Benjamin Marie
46
Multimodal RAG with ColPali and Qwen2-VL on Your Computer
 • Benjamin Marie
11
GRPO: Train LLMs with DeepSeek-R1's Reinforcement Learning Method
 • Benjamin Marie
5
Combine Multiple LoRA Adapters for Llama 2
 • Benjamin Marie
7
Recommendations
View all 10
AI Disruption
AI Disruption
Meng Li
Generative AI Publication
Generative AI Publication
Jim Clyde Monge
AI Tidbits
AI Tidbits
Sahar Mor
AI Horizon Forecast
AI Horizon Forecast
Nikos Kafritsas
Artificial Ignorance
Artificial Ignorance
Charlie Guo
150+ AI Notebooks Now + 2 Each Week:

Tutorials

View all
Gemma 3n: Fine-Tuning, Inference, and Submodel Extraction
Running Gemma 3n with vLLM and fine-tuning with TRL
 • 
Benjamin Marie
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
 • 
Benjamin Marie
4
RTX 6000 Pro vs H100 & A100: Best Single-GPU Choice for Fast, Low-Cost LLM Fine-Tuning
Faster, cheaper single-GPU training
 • 
Benjamin Marie
1
Fine-Tuning 2-Bit Qwen3 Models on Your Computer
Code and best practices
 • 
Benjamin Marie
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?
 • 
Benjamin Marie
© 2025 The Kaitchup
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture