Hugging Face's logo
Activity Feed

AI & ML interests

Accelerating AI by Learning Optimal Datatypes

Recent Activity

Ali93H  new activity 2 days ago
byteshape/Qwen3-4B-Instruct-2507-GGUF:Google 4b and 12b
Ali93H  new activity 5 days ago
byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF:Thinking, coder models
Ali93H  new activity 5 days ago
byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF:gpt-oss-20b?
View all activity

Ali93H 
in byteshape/Qwen3-4B-Instruct-2507-GGUF 2 days ago

Google 4b and 12b

1
#2 opened 3 days ago by
E7Reine
Ali93H 
in byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF 5 days ago

Thinking, coder models

3
#1 opened 11 days ago by
NIK2703

gpt-oss-20b?

2
#5 opened 6 days ago by
Smoffyy
Ali93H 
in byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF 9 days ago

is it supposed to run this slow on a broadwell xeon?

1
#4 opened 9 days ago by
PlatonicSkeptic

Maybe it is not the Instruct-2507 model?

6
#2 opened 10 days ago by
NeoHuggingF

I use this quantized model for RAG, if context is long, always get empty output

7
#3 opened 10 days ago by
gemlincong
Ali93H 
updated a model 9 days ago
Ali93H 
published a model 14 days ago
Ali93H 
in byteshape/Qwen3-4B-Instruct-2507-GGUF about 1 month ago

Moldefile for ollama

3
#1 opened about 1 month ago by
cibernox
Ali93H 
updated 2 models about 1 month ago
Ali93H 
published a model about 1 month ago
Ali93H 
updated 2 models about 1 month ago