Michael Hannecke
ML engineer and writer focused on LLM quantization and deployment. Author of the two-part GGUF deep-dive series.
Known For
- GGUF format internals and quantization mechanics
- Block quantization (Q4_K_M, Q8_0, etc.), K-Quants, I-Quants
- Importance matrix (imatrix) for guided quantization
- Practical LLM deployment with Ollama and llama-server