Ofir Zafrir's picture

Ofir Zafrir

ofirzaf

·

AI & ML interests

Sparsity, Qunatization, Model Compression

Recent Activity

upvoted an article 1 day ago

Intel XPU Kernel Skill: LLM-driven Triton kernel optimization for the Hugging Face Kernel Hub

updated a model 20 days ago

ofirzaf/Qwen3.6-35B-A3B-int4-ov

published a model 20 days ago

ofirzaf/Qwen3.6-35B-A3B-int4-ov

View all activity

Organizations

Articles 3

Article

25

Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models

Article

7

A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake

View all Articles

Papers 5

arxiv:2411.11055

arxiv:2306.16601

arxiv:2211.07715

arxiv:2111.05754

models 3

ofirzaf/Qwen3.6-35B-A3B-int4-ov

Updated 20 days ago • 18

ofirzaf/Qwen3.6-35B-A3B-DFlash-8bit-ov

Updated 20 days ago • 78

ofirzaf/hebrew-math-tutor-v1-W4A16-G128

4B • Updated Feb 10 • 1

datasets 0

None public yet