recursal/RWKV6QwQ-32B-final-250307

The recursal/RWKV6QwQ-32B-final-250307 is a 32 billion parameter RWKV-variant language model developed by recursal, based on the Qwen 2.5 QwQ 32B architecture. This model leverages linear attention to significantly reduce computational costs and improve inference efficiency, particularly for long context lengths. It demonstrates competitive performance across various benchmarks, including ARC Challenge and Winogrande, making it suitable for general language understanding and generation tasks where cost-effective inference is critical.

Cold
Public
32B
FP8
32768
License: apache-2.0
Hugging Face

No reviews yet. Be the first to review!