Halil Sak

halil2002sak

·

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

bartowski/granite-4.2-3b-GGUF

new activity 3 days ago

XHToken/Spark-X2.6-4B:thanks for the model

new activity 18 days ago

JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF:i think we need a mellum 2.1 mini version with 8b a5m version for low end local ai...

View all activity

Organizations

None yet

upvoted 2 collections over 1 year ago

Qwen3

84 items • Updated Dec 31, 2025 • 1.87k

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 21 • 219