The Kaitchup – AI on a Budget

The Kaitchup – AI on a Budget

Home
Notes
AI Notebooks
The Kaitchup Pro
The Kaitchup's Book
AI Toolboxes
Tutorials
Archive
About
Llama 4 with 10M Tokens: How Much Does It Cost and Is It Worth It?
A KV Cache Story
 • 
Benjamin Marie
Fine-Tuning Gemma 3 on Your Computer with LoRA and QLoRA (+model review)
The efficiency of global-local attention with QK-Norm and no more soft-capping
 • 
Benjamin Marie
7
Make LLMs Faster and Lighter with W8A8 Quantization
Efficient Weight and Activation Quantization with llm-compressor
 • 
Benjamin Marie
The Weekly Kaitchup #88
Nemotron-H - 1-bit LLM
 • 
Benjamin Marie
Run Llama 3.3 70B on Your GPU with ExLlamaV3
Fast Llama 3.3 70B at 1.75 bits per weight, using only 19 GB!
 • 
Benjamin Marie
1
150+ AI Notebooks Now + 2 Each Week:

Recent posts

View all
Fast and Memory-Efficient Full Fine-Tuning with Unsloth (single-GPU)
With the best hyperparameters for a cost-effective full fine-tuning
 • 
Benjamin Marie
4
The Weekly Kaitchup #87
Llama 4 - MoE-Quant - Nemotron Ultra
 • 
Benjamin Marie
Llama 4 Scout, Maverick, and Behemoth: MoE, VLMs, and Very Long Context
How to burn GPUs
 • 
Benjamin Marie
The Weekly Kaitchup #86
Gemma 3 QAT - Dream 7B
 • 
Benjamin Marie
LoRA Trainable Tokens: Save Memory, Improve Accuracy for Your Domain
How to teach an LLM to use your new tokens without fully retraining the token embeddings
 • 
Benjamin Marie
vLLM v1 Engine: How Faster Is It for RTX and Mid-Range GPUs?
Better design and faster with H100s but what about the smaller GPUs?
 • 
Benjamin Marie
2
The Weekly Kaitchup #85
Qwen2.5-Omni-7B - DPO vs. PPO - DeepSeek-V3 Update - GPTQ Models
 • 
Benjamin Marie
Fine-Tuning and Inference with an RTX 5090
Is the RTX 5090 noticeably faster than the previous generation for LLMs?
 • 
Benjamin Marie
© 2025 The Kaitchup
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture