Hugging Face's logo
Ed Addario's picture
🏗️ Building on HF

Ed Addario PRO

eaddario
22 9 9
YellowjacketGames's profile picture assasin-22's profile picture seshurajup's profile picture
·

AI & ML interests

Finding ways to optimize LLMs' inference performance in resource-constrained environments (e.g. commodity hardware, desktops, laptops, mobiles, edge devices, etc.)

Recent Activity

posted an update 8 days ago
Experimental JQK and global target bits‑per‑weight quantization of Nanbeige/Nanbeige4.3-33B. Unlike standard llama.cpp quantization that relies on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach automatically optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global size target. Key Advantages: - Better model quality: using JQK types can improve KLD between 10% to 50% compared to standard QK types, at the same bpw. - VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM). - Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs. Information about JQK types: https://huggingface.co/eaddario/JQ2_K-JQ6_K-Test-Models Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the model's cards. JQK Quantization: https://huggingface.co/eaddario/Nanbeige4.3-33B-JQK Global target BPW: https://huggingface.co/eaddario/Nanbeige4.3-33B-GGUF
updated a model 8 days ago
eaddario/Nanbeige4.3-33B-GGUF
updated a model 8 days ago
eaddario/Nanbeige4.3-33B-JQK
View all activity

Organizations

Hugging Face Discord Community's profile picture