Qwen3.6-35B-A3B-GGUF (Unsloth)

Unsloth's GGUF-quantized packaging of Alibaba's Qwen3.6-35B-A3B sparse mixture-of-experts model, enabling local and self-hosted inference on consumer-grade hardware via llama.cpp and compatible runtimes. The model features 35B total parameters with only 3B active per token and a 262K-token native context window. Source: supabase.