Intel

/

Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound

like 29

Follow

Intel 3.17k

CPU/CUDA

For Intel GPU, please use this one https://huggingface.co/Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound

Is it possible to pack Qwen3-Next-80B-A3B-Thinking-int4-AutoRound into Openvino format?

Would be the icing on the cake

Is it possible to pack Qwen3-Next-80B-A3B-Thinking-int4-AutoRound into Openvino format?

Would be the icing on the cake

Suggest adding the support of recognizing the autoround format (see the bottom lines of config.json), which is compatible with GPTQ. Meanwhile, you may consider supporting the mixed precision: MoE Linear INT4, and non-MoE linears INT8. Happy to collaborate to enable AutoRound into OpenVINO!