Feature Request: please ad support to model architecture: 'qwen4exp'

[dan64]

Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

build 10708 (34d749c) with MSVC 19.44.35228.0 for Windows AMD64

Please add support to model architecture: 'qwen4exp'

Motivation

I cannot load the model unsloth\Qwen3.8-Flash-Next-GGUF\UD-IQ3_XXS

error:

[50386] 0.00.490.263 I print_info: file format = GGUF V3 (latest)
[50386] 0.00.490.264 I print_info: file type   = IQ3_XXS - 3.0625 bpw
[50386] 0.00.490.267 I print_info: file size   = 76.32 GiB (3.71 BPW)
[50386] 0.00.509.535 E llama_model_load: error loading model: unknown model architecture: 'qwen4exp'
[50386] 0.00.509.541 E llama_model_load_from_file_impl: failed to load model
[50386] 0.00.509.547 E cmn  common_init_: failed to load model 'C:\models\unsloth\Qwen3.8-Flash-Next-GGUF\UD-IQ3_XXS\Qwen3.8-Flash-Next-UD-IQ3_XXS-00001-of-00003.gguf'

Possible Implementation

No response