Eugene Oskin

eoskin's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Paper • 1910.01108 • Published Oct 2, 2019 • 23

liked 2 models 1 day ago

Qwen/Qwen3.6-35B-A3B

Image-Text-to-Text • 36B • Updated 22 days ago • 4.94M • • 1.78k

Qwen/Qwen3.6-35B-A3B-FP8

Image-Text-to-Text • 36B • Updated 22 days ago • 4.59M • 216

upvoted a collection 1 day ago

Qwen3.6

Collection

4 items • Updated 24 days ago • 347

upvoted 2 papers 2 days ago

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

Paper • 2605.09530 • Published 6 days ago • 139

Efficient Pre-Training with Token Superposition

Paper • 2605.06546 • Published 9 days ago • 35

upvoted a paper 3 days ago

MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE

Paper • 2505.19645 • Published Feb 16 • 1

liked 2 models 3 days ago

unsloth/Qwen3.6-27B-MTP-GGUF

Image-Text-to-Text • 27B • Updated about 21 hours ago • 105k • 169

unsloth/Qwen3.6-35B-A3B-MTP-GGUF

Image-Text-to-Text • 36B • Updated about 21 hours ago • 97.7k • 150

upvoted an article 3 days ago

view article

Article

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

• 

RakshitAralimatti

•

Aug 8, 2025

• 35

upvoted a paper 3 days ago

SD-MoE: Spectral Decomposition for Effective Expert Specialization

Paper • 2602.12556 • Published Feb 13 • 1

liked a model 4 days ago

Qwen/WebWorld-8B

Text Generation • 8B • Updated 8 days ago • 903 • • 41

upvoted a paper 4 days ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published 9 days ago • 182

liked 6 models 4 days ago

unsloth/Qwen3.6-27B-UD-MLX-4bit

Image-Text-to-Text • 10B • Updated 23 days ago • 101k • 48

unsloth/Qwen3-Coder-Next-GGUF

Text Generation • 80B • Updated Mar 6 • 748k • 627

eoskin/Qwopus3.6-35B-A3B-v1-mlx-4Bit

Image-Text-to-Text • 35B • Updated 4 days ago • 217 • 1

mlx-community/Qwen3.6-35B-A3B-4bit

Image-Text-to-Text • 6B • Updated 29 days ago • 114k • 50

mlx-community/Qwen3-Coder-Next-4bit

Text Generation • Updated Feb 7 • 7.13k • 21

Intel/Qwen3.6-27B-4.5b-mlx-AutoRound

7B • Updated 18 days ago • 340 • 20

updated a model 4 days ago

eoskin/Qwopus3.6-35B-A3B-v1-mlx-4Bit

Image-Text-to-Text • 35B • Updated 4 days ago • 217 • 1