Suite of Qwen 3 models, compressed using sparsification and 4-bit floating point precision for low-resource deployment.
Cortecs
company
Verified
AI & ML interests
Europe's AI Enabler
Recent Activity
View all activity
Organization Card
Our Sky Inference is a next-generation AI deployment platform built on the principles of sky computing: a unified, resilient, and scalable approach to compute that spans across multiple cloud providers. Instead of being tied to a single vendor, Sky Inference dynamically routes AI workloads across a network of GDPR-compliant European providers, automatically optimizing for performance, cost, and availability.
models
28
cortecs/Qwen3-8B-clean-sparse-finetuned-0.01-nvfp4a16
5B
•
Updated
•
5
cortecs/Qwen3-8B-clean-sparse
6B
•
Updated
•
9
cortecs/Qwen3-8B-clean-sparse-finetuned-0.1-nvfp4a16
5B
•
Updated
•
9
cortecs/Qwen3-8B-clean-sparse-nvfp4a16
5B
•
Updated
•
11
cortecs/Qwen3-8B-NVFP4A16
5B
•
Updated
•
8
cortecs/Qwen3-8B-NVFP4
5B
•
Updated
•
19
cortecs/lorastral24b_0604-FP8-Dynamic
Text Generation
•
24B
•
Updated
•
7
•
1
cortecs/Phi-4-reasoning-plus-FP8-Dynamic
15B
•
Updated
•
22
•
2
cortecs/QwQ-32B-FP8-Dynamic
33B
•
Updated
•
16
•
1
cortecs/r1-1776-distill-llama-70b-FP8-Dynamic
Text Generation
•
71B
•
Updated
•
5
•
2
datasets
0
None public yet