Alibaba, abliterated by huihui-ai
Qwen 3.6 35B-A3B Abliterated
Qwen 3.6 35B-A3B Abliterated is a mixture-of-experts model that runs 3B of its 36B parameters per token, and it fits one 24 GB GPU.
Rank#7 / 8
#7Editors' rankingSize#5 / 8
36BTotal, 3B activePrice
FreeOpen weights you run yourselfRuns on
24 GB GPUAbout 22 GB at 4-bitOur pick for a mixture-of-experts model on a home GPU.
Input
Model id
huihui-ai/Huihui-Qwen3.6-35B-A3B-abliteratedIts MTP GGUF build had over 5 million downloads on Hugging Face in the last month.
Run it yourself
SizeAbout 22 GB at 4-bit
HardwareOne 24 GB GPU
LicenseApache 2.0
Load a GGUF build in Ollama, LM Studio or llama.cpp. When a job outgrows one GPU, run DeepSeek V4.1 Flash Abliterated on Silk Compute.