Hugging Face's Local AI 301 livestream: four talks on quantization with bartowski and Labonne
Hugging Face · youtube · 2026-11-05
Hugging Face is running a livestream, "Local AI 301: Quantization" — 4 talks plus live Q&A on Nov 10, 9AM PST / 6PM CET:
- Intro to Quantization — Merve Noyan (Hugging Face)
- Calibration-based quantization — Colin Kealty (aka bartowski, Red Hat)
- Quantization-Aware Distillation — Maxime Labonne & Aditya Tadimeti (Liquid AI)
- Fast microscaling formats on any GPU with vLLM — Michael Goin (Red Hat)
Aimed at practitioners getting started with quantization via llama.cpp and vLLM, featuring well-known community quantizers and the Liquid AI research team.
Related event: Hugging Face to Host Local AI 301 Livestream on Model Quantization(4 posts)→
More from Infra
- Trainium's biggest hurdle isn't the chip — it's the CUDA ecosystem — DavidLinthicum · 2026-11-05
- Nebius auto-tuner speeds RL training up to 5x on fixed GPU budgets — demian_ai · 2026-11-05
- After communities vote against data centers, OpenAI pledges to pay power bills — ross2000 · 2026-11-05
- DeepSeek V4.1 streaming EXL3 packs bring ~70 tok/s local inference to 128GB Macs — HankYeomans · 2026-11-05
- 137 internal Google schemas reveal exactly what NavBoost remembers about every search — jedisct1 · 2026-11-05
- After 27 years of self-hosting, blogger shutters his own servers — genmon · 2026-11-05