Embedl

embedl's activity

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

WilhelmT 

updated 3 models 11 days ago

embedl/Cosmos-Reason2-2B-W4A16

Image-Text-to-Text • 2B • Updated 11 days ago • 2.32k • 6

embedl/Cosmos-Reason2-2B-W4A16-Edge2

Image-Text-to-Text • 2B • Updated 11 days ago • 24.4k • 11

embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead

Image-Text-to-Text • 2B • Updated 11 days ago • 749 • 6

WilhelmT 

updated a Space 11 days ago

Running

4

Edge Inference Benchmarks

🚀

4

On-Device benchmarks across devices and models.

HProg 

updated a model 12 days ago

embedl/Cosmos-Reason2-2B-W4A16-Edge2

Image-Text-to-Text • 2B • Updated 11 days ago • 24.4k • 11

JonnaMat 

updated 4 collections 12 days ago

NVIDIA Jetson Orin Nano

Collection

Ultra-efficient model variants optimized for Jetson Orin Nano. Designed for constrained edge environments requiring low memory footprint. • 4 items • Updated 12 days ago • 2

NVIDIA Jetson AGX Thor

Collection

Models validated and performance-optimized for NVIDIA Jetson AGX Thor. Tailored for high-performance edge AI workloads. • 5 items • Updated 12 days ago • 1

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. • 4 items • Updated 12 days ago • 2

Cosmos-Reason2

Collection

nvidia/Cosmos-Reason2 multi-modal reasoning models optimized by Embedl. • 9 items • Updated 12 days ago • 4

JonnaMat 

updated a model 15 days ago

embedl/Cosmos-Reason2-2B-W4A16-Edge2

Image-Text-to-Text • 2B • Updated 11 days ago • 24.4k • 11

JonnaMat 

updated a Space 15 days ago

Running

4

Edge Inference Benchmarks

🚀

4

On-Device benchmarks across devices and models.

JonnaMat 

in embedl/Edge-Inference-Benchmarks 15 days ago

Demo

#5 opened 17 days ago by

JonnaMat

JonnaMat 

updated a dataset 15 days ago

embedl/documentation-images

Viewer • Updated 15 days ago • 7 • 3.56k

JonnaMat 

updated 2 collections 15 days ago

Cosmos-Reason2

Collection

nvidia/Cosmos-Reason2 multi-modal reasoning models optimized by Embedl. • 9 items • Updated 12 days ago • 4

EdgeN

Collection

Quantization strategy where most weights are converted to INT4, activations remain in FP16, and sensitive layers are preserved in FP16. • 5 items • Updated 15 days ago • 1