Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: quantization
BitNet and Cassandra: How Ternary Weights Speed Up Local LLMs on CPUs
Six findings on 1.58-bit BitNet, speculative decoding and the Cassandra framework: up to 6.17x faster on x86, 82.2% less energy and no accuracy loss.
949 wordsRead articleHow QLoRA Fine-Tunes Large Models on Small GPUs: 4-bit Basics
Understand QLoRA from the ground up: why full fine-tuning is expensive, how LoRA adapters and 4-bit quantization combine, and when this approach fits your project.
1834 wordsRead articleVector Quantization Compared: Int8 Versus Binary Recall and Storage
Measure how int8 and binary quantization change recall and storage for embeddings, why binary can collapse, and how to choose a safe compression level.
940 wordsRead articleHardware reality check for running 100B-class models locally
MoE sparsity, quantization, and VRAM math decide whether 100B-class weights fit a workstation—not parameter marketing.
2477 wordsRead articleWhen Quantization Passes Perplexity and Silently Breaks Model Safety
Low-bit KV cache quantization can wipe out a model's refusals while perplexity barely moves; here is why the standard metrics miss it and what to add to your gate.
1625 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.