hyperhuzaifa/Qwen3.6-35B-A3B-IK-K-GGUF

Add model card + ik_llama.cpp usage instructions

add qwen35moe-IQ6_K.gguf: ik_llama IQ6_K self-quant of Qwen 3.6 35B-A3B (26.8 GB)

add qwen35moe-IQ5_K.gguf: ik_llama IQ5_K self-quant of Qwen 3.6 35B-A3B (22.3 GB)

add qwen35moe-IQ4_K.gguf: ik_llama IQ4_K self-quant of Qwen 3.6 35B-A3B (18.4 GB)

Add qwen35moe.imatrix

initial commit