Eugene Oskin

eoskin's activity

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

liked a model about 6 hours ago

Qwen/WebWorld-8B

Text Generation • 8B • Updated 4 days ago • 279 • 30

upvoted a paper about 8 hours ago

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

Paper • 2605.06169 • Published 6 days ago • 116

liked 4 models about 10 hours ago

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

Image-Text-to-Text • 10B • Updated 20 days ago • 91k • 44

unsloth/Qwen3-Coder-Next-GGUF

Text Generation • 80B • Updated Mar 6 • 307k • 626

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

Image-Text-to-Text • 35B • Updated about 20 hours ago • 1

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

Image-Text-to-Text • 6B • Updated 26 days ago • 102k • 47

liked 2 models about 19 hours ago

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

Text Generation • Updated Feb 7 • 7.23k • 21

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

7B • Updated 15 days ago • 337 • 20

updated a model about 20 hours ago

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

Image-Text-to-Text • 35B • Updated about 20 hours ago • 1

published a model about 20 hours ago

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

Image-Text-to-Text • 35B • Updated about 20 hours ago • 1

liked a Space about 20 hours ago

Running

Agents

191

MLX My Repo

🐐

191

Convert and upload models to Hugging Face

liked a model about 20 hours ago

Jackrong/Negentropy-claude-opus-4.7-9B-GGUF

Image-Text-to-Text • 9B • Updated 5 days ago • 6.22k • 24

liked 2 models about 21 hours ago

mlx-community/gemma-4-26b-a4b-it-4bit

Image-Text-to-Text • 5B • Updated 29 days ago • 50.5k • 53

unsloth/Mistral-Medium-3.5-128B-GGUF

125B • Updated 10 days ago • 52.2k • 49

upvoted an article 1 day ago

view article

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

• 

not-lain

•

Jan 30, 2025

• 326

upvoted a collection 5 days ago

🍎 Qwopus3.6

Collection

This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e • 4 items • Updated 6 days ago • 41

liked a model 6 days ago

Jackrong/Qwopus3.6-35B-A3B-v1-GGUF

Image-Text-to-Text • 35B • Updated 6 days ago • 67.2k • 115

upvoted a paper 6 days ago

Thinking with Drafting: Optical Decompression via Logical Reconstruction

Paper • 2602.11731 • Published Feb 12 • 35

liked 2 models 8 days ago

unsloth/granite-4.1-30b-GGUF

29B • Updated 12 days ago • 23.1k • 17

ibm-granite/granite-4.1-30b

Text Generation • 29B • Updated 8 days ago • 14.8k • 110