mudler author hub

Qwen3.6 35B A3B NVFP4 GGUF NVFP4 native Blackwell FP4 GGUF of Qwen3.6 35B A3B Mixture of Experts, ~3B active parameters per token . A single file, FP4 native quantization that runs on LocalAI's paged attention llama.cpp backend with strong decode throughput and a low memory foot…