embedl/Cosmos-Reason2-2B-W4A16-Edge2
Image-Text-to-Text • 2B • Updated
• 10.6k • 10
AI & ML interests
None defined yet.
Recent Activity
View all activity
HProgÂ
updated a model about 2 hours ago
Add accuracy data
#4 opened about 3 hours ago
by
JonnaMat
JonnaMatÂ
updated a Space about 4 hours ago
Add subgroups to sidebar
#3 opened about 5 hours ago
by
JonnaMat
Post
139
Qwen3.5 on-device benchmarks on the Nvidia Jetson lineup are now live 🚀
We've added the latest Qwen3.5 models (0
8B - 9B) to our on-device inference benchmarks (Nvidia Jetson Orin Nano Super, AGX Orin, AGX Thor).
👉 Explore TPS, TTFT, E2E latency, and TPOT. Measured on real hardware: embedl/Edge-Inference-Benchmarks
🌟 Stay tuned for additional benchmarks and Embedl-optimized models: Enabling models run faster and on less expensive hardware.
If you're working on edge LLM deployment, we'd love to discuss your use case.
We've added the latest Qwen3.5 models (0
8B - 9B) to our on-device inference benchmarks (Nvidia Jetson Orin Nano Super, AGX Orin, AGX Thor).
👉 Explore TPS, TTFT, E2E latency, and TPOT. Measured on real hardware: embedl/Edge-Inference-Benchmarks
🌟 Stay tuned for additional benchmarks and Embedl-optimized models: Enabling models run faster and on less expensive hardware.
If you're working on edge LLM deployment, we'd love to discuss your use case.
-
- 1 reply
Add Qwen3.5 Benchmarks
#2 opened 1 day ago
by
JonnaMat
Update chart and table styling
#1 opened 1 day ago
by
JonnaMat
JonnaMatÂ
updated 3 models 3 days ago
JonnaMatÂ
published a Space 3 days ago
JonnaMatÂ
updated a dataset 3 days ago
JonnaMatÂ
updated a collection 7 days ago