Building on HF

16 5 8

Ed Addario PRO

eaddario

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

new activity 5 days ago

eaddario/Qwen3.5-9B-GGUF:Amazing quants

new activity 7 days ago

Lucebox/Laguna-XS.2-GGUF:Steps to convert to GGUF?

updated a model 9 days ago

eaddario/granite-4.1-30b-GGUF

View all activity

Organizations

upvoted an article 6 months ago

Article

Norm-Preserving Biprojected Abliteration

grimjim

•

Nov 6, 2025

• 81

upvoted 2 articles about 1 year ago

Article

Cohere on Hugging Face Inference Providers 🔥

reach-vb, burtenshaw, merve, celinah, alexrs, julien-c, sbrandeis

•

Apr 16, 2025

• 129

Article

Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach

oopere

•

Nov 24, 2024

• 20

upvoted a collection about 1 year ago

Dolphin 3.0

Collection

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 9 items • Updated Feb 7, 2025 • 201

upvoted a collection over 1 year ago

Unsloth 4-bit Dynamic Quants

Collection

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated 30 days ago • 96

Ed Addario PRO

AI & ML interests

Recent Activity

Organizations

eaddario's activity

Norm-Preserving Biprojected Abliteration

Cohere on Hugging Face Inference Providers 🔥

Making LLMs Smaller Without Breaking Them: A GLU-Aware Pruning Approach