Yooz Labs Dev

YoozDev's activity

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

updated a collection 3 days ago

Lean QAT MLX

Collection

QAT quality at honest 4-bit size for Apple Silicon: uniform 4-bit g64 MLX builds, no silent 8-bit upgrades. Yooz Labs (yooz.live). • 4 items • Updated 3 days ago

updated 4 models 3 days ago

YoozLabs/Qwen3.5-4B-qat-GGUF

Text Generation • 4B • Updated 3 days ago • 26

YoozLabs/Qwen3.5-0.8B-qat-GGUF

Text Generation • 0.8B • Updated 3 days ago • 24

YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx

Text Generation • 0.7B • Updated 3 days ago • 55

YoozLabs/Qwen3.5-0.8B-qat-lean-4bit-mlx

Text Generation • 0.1B • Updated 3 days ago • 57

published 4 models 3 days ago

YoozLabs/Qwen3.5-4B-qat-GGUF

Text Generation • 4B • Updated 3 days ago • 26

YoozLabs/Qwen3.5-0.8B-qat-GGUF

Text Generation • 0.8B • Updated 3 days ago • 24

YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx

Text Generation • 0.7B • Updated 3 days ago • 55

YoozLabs/Qwen3.5-0.8B-qat-lean-4bit-mlx

Text Generation • 0.1B • Updated 3 days ago • 57

updated a dataset 4 days ago

YoozLabs/transit-guest-images

Viewer • Updated 4 days ago • 1 • 15

published a dataset 4 days ago

YoozLabs/transit-guest-images

Viewer • Updated 4 days ago • 1 • 15

updated 2 models 4 days ago

YoozLabs/gemma-4-12B-it-qat-lean-4bit-mlx

Text Generation • 12B • Updated 4 days ago • 175

YoozLabs/gemma-4-E4B-it-qat-lean-4bit-mlx

Text Generation • 1B • Updated 4 days ago • 122

updated a collection 5 days ago

Lean QAT MLX

Collection

QAT quality at honest 4-bit size for Apple Silicon: uniform 4-bit g64 MLX builds, no silent 8-bit upgrades. Yooz Labs (yooz.live). • 4 items • Updated 3 days ago

published 2 models 5 days ago

YoozLabs/gemma-4-12B-it-qat-lean-4bit-mlx

Text Generation • 12B • Updated 4 days ago • 175

YoozLabs/gemma-4-E4B-it-qat-lean-4bit-mlx

Text Generation • 1B • Updated 4 days ago • 122

updated a model 23 days ago

YoozLabs/YoozTextCleanup

Updated 23 days ago