Andrej Baranovskij

katanaml's activity

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

upvoted a collection 5 days ago

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory. • 19 items • Updated 5 days ago • 24

liked 3 models 27 days ago

mlx-community/Mistral-Small-3.1-24B-Instruct-2503-8bit

Updated Mar 19 • 322 • 1

mlx-community/Mistral-Small-3.1-24B-Instruct-2503-bf16

Updated Mar 19 • 133 • 2

mlx-community/Qwen2.5-VL-32B-Instruct-bf16

Image-Text-to-Text • Updated 27 days ago • 272 • 4

liked a model 28 days ago

mlx-community/Qwen2.5-VL-32B-Instruct-8bit

Image-Text-to-Text • Updated 27 days ago • 564 • 4

liked a model about 1 month ago

mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit

Updated Mar 19 • 878 • 4

upvoted a collection about 1 month ago

Gemma 3

Collection

A collection of lightweight, state-of-the-art open models built from the same research and technology that powers the Gemini 2.0 models • 31 items • Updated Mar 12 • 23

upvoted an article about 1 month ago

view article

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Mar 12

• 398

upvoted a collection about 2 months ago

Qwen2.5-VL

Collection

22 items • Updated 30 days ago • 7

liked 7 models 3 months ago

mlx-community/Qwen2.5-VL-7B-Instruct-8bit

Image-Text-to-Text • Updated Feb 25 • 4.76k • 15

mlx-community/Qwen2.5-VL-72B-Instruct-4bit

Image-Text-to-Text • Updated Feb 25 • 262 • 6

mlx-community/Qwen2.5-VL-7B-Instruct-bf16

Image-Text-to-Text • Updated Feb 26 • 167 • 3

mlx-community/Qwen2.5-VL-72B-Instruct-6bit

Image-Text-to-Text • Updated Feb 25 • 28 • 1

Qwen/Qwen2.5-VL-3B-Instruct

Image-Text-to-Text • Updated 17 days ago • 1.24M • 337

Qwen/Qwen2.5-VL-7B-Instruct

Image-Text-to-Text • Updated 17 days ago • 2.42M • • 836

Qwen/Qwen2.5-VL-72B-Instruct

Image-Text-to-Text • Updated Mar 23 • 161k • • 431

upvoted a collection 3 months ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 11 items • Updated 23 days ago • 446

liked a Space 4 months ago

Running

566

566

QVQ 72B Preview

🌍

Upload images and ask questions to get answers

upvoted a collection 4 months ago

DeepSeek-VL2

Collection

14 items • Updated Dec 22, 2024 • 6

liked a model 4 months ago

mlx-community/deepseek-vl2-8bit

Image-Text-to-Text • Updated Jan 2 • 53 • 5