Embedl

embedl's activity

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

HProg 

posted an update about 17 hours ago

view post

Post

47

📣 I made a visualizer for Hugging Face models: https://hfviewer.com

✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!

🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B

Feel free to try it out and give me feedback on how it can be improved! ❤️

See translation

• 

Reply

JonnaMat 

updated 4 models 5 days ago

embedl/Qwen3.5-9B-FlashHead

Image-Text-to-Text • 10B • Updated 5 days ago • 410

embedl/Qwen3.5-4B-FlashHead

Image-Text-to-Text • 5B • Updated 5 days ago • 424

embedl/Qwen3.5-0.8B-FlashHead

Image-Text-to-Text • 0.9B • Updated 5 days ago • 372

embedl/Qwen3.5-2B-FlashHead

Image-Text-to-Text • 2B • Updated 5 days ago • 436

JonnaMat 

posted an update 5 days ago

view post

Post

94

⚡ Qwen3.5, up to 1.4× faster. Same quality. Less latency.

We applied FlashHead to the Qwen3.5 family: Novel drop-in replacement of the LM head with measurably lower latency on edge hardware. Benchmarks and models below.

📊 embedl/Edge-Inference-Benchmarks

🤗 https://huggingface.co/collections/embedl/qwen35

See translation

• 

🔥

1

1

+

Reply

JonnaMat 

updated 6 collections 5 days ago

NVIDIA Jetson AGX Orin

Collection

Models optimized and bench-marked for NVIDIA Jetson AGX Orin. Memory-efficient and latency-optimized variants designed for real-time edge inference. • 8 items • Updated 5 days ago • 3

NVIDIA Jetson AGX Thor

Collection

Models validated and performance-optimized for NVIDIA Jetson AGX Thor. Tailored for high-performance edge AI workloads. • 7 items • Updated 5 days ago • 1

FlashHead

Collection

Efficient Drop-In Replacement for the Classification Head in Language Model Inference. https://github.com/embedl/flash-head • 24 items • Updated 5 days ago • 2

EdgeN

Collection

Quantization strategy where most weights are converted to INT4, activations remain in FP16, and sensitive layers are preserved in FP16. • 4 items • Updated 5 days ago • 1

Qwen3.5

Collection

Qwen/Qwen3.5 variants optimized by embedl. • 6 items • Updated 5 days ago • 1

NVIDIA Jetson Orin Nano

Collection

Ultra-efficient model variants optimized for Jetson Orin Nano. Designed for constrained edge environments requiring low memory footprint. • 5 items • Updated 5 days ago • 4

JonnaMat 

updated a dataset 5 days ago

embedl/documentation-images

Viewer • Updated 5 days ago • 12 • 2.22k

JonnaMat 

published 3 models 5 days ago

embedl/Qwen3.5-27B-FlashHead

Image-Text-to-Text • 28B • Updated 7 days ago • 254

embedl/Qwen3.5-9B-FlashHead

Image-Text-to-Text • 10B • Updated 5 days ago • 410

embedl/Qwen3.5-4B-FlashHead

Image-Text-to-Text • 5B • Updated 5 days ago • 424