The Kaitchup – AI on a Budget
Subscribe
Sign in
Home
Notes
AI Notebooks
The Kaitchup's Book
Weekly Kaitchup
Tutorials
The Kaitchup Index
Archive
About
Weekly Kaitchup
Latest
Top
Discussions
More Qwen3.5 GGUF Evals and Speculative Speculative Decoding (SSD)
The Weekly Kaitchup #133
Mar 6
•
Benjamin Marie
8
Lessons from GGUF Evaluations: Ternary Qwen3.5, Bricked Minimax
The Weekly Kaitchup #132
Feb 27
•
Benjamin Marie
11
8
2
Taalas HC1: Absurdly Fast, Per-User Inference at 17,000 tokens/second
The Weekly Kaitchup #131
Feb 20
•
Benjamin Marie
24
1
2
Nanbeige4.1: Only 3B Parameters, but as Good as Qwen3 32B?
The Weekly Kaitchup #130
Feb 14
•
Benjamin Marie
6
LoRA but with Only 13 Parameters??
The Weekly Kaitchup #129
Feb 6
•
Benjamin Marie
8
This Week: Arcee Trinity and Quantization-Aware Distillation
The Weekly Kaitchup #128
Jan 30
•
Benjamin Marie
9
3
This Week: GLM 4.7 Flash's Huge KV Cache and LFM2.5 Thinking
The Weekly Kaitchup #127
Jan 23
•
Benjamin Marie
8
MMLU-Pro Has an Answer Leak (and It’s Just Whitespace)
The Weekly Kaitchup #126
Jan 16
•
Benjamin Marie
6
LFM2.5 and Falcon H1R-7B: New Hybrid Models with Strong Benchmark Scores
The Weekly Kaitchup #125
Jan 9
•
Benjamin Marie
6
3
2
2026 Predictions: Much Faster Inference, Pre-Training with RL, and FP4 Everywhere
The Weekly Kaitchup #124
Jan 2
•
Benjamin Marie
12
Encoder–Decoders and Byte LLMs: T5Gemma 2 and AI2’s New Models
The Weekly Kaitchup #123
Dec 19, 2025
•
Benjamin Marie
8
2
2
Notes on RNJ-1, K2-V2, Devstral 2, and GLM-4.6V
The Weekly Kaitchup #122
Dec 12, 2025
•
Benjamin Marie
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
