Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
🏗️
Building on HF
77.8
TFLOPS
Ed Addario
PRO
eaddario
22
9
9
Follow
assasin-22's profile picture
Jordiva7's profile picture
sudanenator's profile picture
143 followers
·
36 following
EAddario
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
10 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
10 days ago
eaddario/Nanbeige4.3-33B-GGUF
updated
a model
11 days ago
eaddario/Nanbeige4.3-33B-JQK
View all activity
Organizations
eaddario
's datasets
2
Sort: Recently updated
eaddario/imatrix-calibration
Viewer
•
Updated
May 5
•
299
•
9.53k
•
77
eaddario/benchmark
Updated
May 2
•
14