Ed Addario PRO
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 8 days ago
eaddario/Qwen3.6-27B-GGUF:nice work man new activity 8 days ago
eaddario/Qwen3.6-27B-GGUF:Best Qwen3.6-27B that fit in 16 GBOrganizations
Dolphin-Mistral-24B-Venice-Edition-heretic mmproj Q8_0 – experimental img_break fix
2
#1 opened 3 days ago
by 
DokMeMoRiA
nice work man
1
#3 opened about 2 months ago
by 
qenme
Best Qwen3.6-27B that fit in 16 GB
❤️🤝 2
3
#4 opened 25 days ago
by 
tsewaiho
Qwen3.8-27B has been released
👍 1
1
#5 opened 17 days ago
by 
chentel
Great quants! 122b?
1
#1 opened 2 months ago
by 
dicksondickson
Methodology of using F16 as intermediate conversion and baseline?
2
#1 opened 4 months ago
by 
RyanoSaurus-Wrex
Amazing quants
4
#2 opened 5 months ago
by 
IrisColt
Steps to convert to GGUF?
#1 opened 4 months ago
by eaddario
interessting but comparison
5
#1 opened 5 months ago
by 
kalle07
Is there a mmproj file?
3
#1 opened 5 months ago
by dicksondickson
Great collection, I'm using it for my little project.
10
#5 opened 6 months ago
by 
cmh
Request to add SEA language dataset.
4
#4 opened 6 months ago
by 
MagicalAlchemist
HuggingFaceFW/finepdfs 3T tokens of non-GPT slop
❤️ 1
2
#2 opened 12 months ago
by 
Joseph717171
Parquet file is toxic?
1
#3 opened 7 months ago
by 
sebastienbo
Will GLM-4.6-Air model be released?
❤️🚀 9
8
#15 opened 10 months ago
by 
ddh0
GitHub account and ik_llama.cpp are down?!
😔👍 4
60
#2 opened about 1 year ago
by 
ubergarm
Interesting comparisons!
11
#1 opened over 1 year ago
by ubergarm
🚩 Report: Illegal or restricted content
1
#2 opened over 1 year ago
by 
JLouisBiz
[BUG] Model does not support tools in Ollama
👀 1
1
#1 opened over 1 year ago
by 
liemkg1234
Problem with the license, this is not really free software
3
#1 opened over 1 year ago
by JLouisBiz