The Kaitchup
Newsletter · Open Source & Coding · kaitchup.substack.com
Tutorials on adapting LLMs to your tasks and hardware on a budget.
Summary written from the source’s own About page · checked 2026-11-21
Latest Posts
Titles link to the original on kaitchup.substack.com. We never copy article text.
- kaiLLM and kaiPTQ: Building My Own Inference Engine for Low-Bit ModelsNov 21 01:11 UTC
- Hy4 Flash vs. Qwen3.8 Flash Next: Architecture, KV Cache, and Token EfficiencyNov 19 03:37 UTC
- Black Friday: 30% Off, Plus Qwen3.8 27B on a 12 GB GPUNov 17 19:51 UTC
- Inkling 2 Small: 594B Parameters, Trained in NVFP4Nov 13 20:29 UTC
- DSpine Speculative Decoding: 4x Faster Coding Agents on One GPUNov 12 21:28 UTC
Publishing Activity
Posts per week over the last 12 weeks, from its feed
Similar Sources
Same main topic: Open Source
- YouTube
Olivio Sarikas
AI art: local image models and install guides.
- YouTube
Fahd Mirza
Daily hands-on tests of AI models and tools, local and cloud.
- Blog
vLLM Blog
Technical articles and releases from the vLLM open-source inference project.
- Lab Blog
Hugging Face Blog
Hugging Face on open-source models, tools and open science.
Posts daily
How these numbers are made: we read this source’s public feed every 6 hours. Posting rate, last post, topic mix and “first to report” come from that feed and from how we group stories across all sources. We never show ratings or reviews. Read the methodology →