QuantTrio/Qwen3.6-35B-A3B-AWQ

A third-party AWQ 4-bit quantized derivative of Alibaba's Qwen3.6-35B-A3B sparse Mixture-of-Experts model, packaged by QuantTrio for efficient local and self-hosted inference. The underlying base model has 35B total parameters with approximately 3B activated per token and supports text, image, and video modalities. Source: supabase.