Feature Request: Support GLM5.3 (flash)

[mirek-vl]

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

Add support for glm5.3 models. Currently with flash I get the following error:

E mtmd_get_memory_usage: error: Failed to load CLIP model from /.cache/huggingface/hub/models--unsloth--GLM-5.3-Flash-GGUF/snapshots/d425e572fb9686125831f476129e51cea34bc5b4/mmproj-BF16.gguf
E srv    load_model: [mtmd] failed to get memory usage of mmproj
E llama_model_load: error loading model: unknown model architecture: 'glm5next'
E llama_model_load_from_file_impl: failed to load model
E common_fit_params: encountered an error while trying to fit params to free device memory: failed to load model
E llama_model_load: error loading model: unknown model architecture: 'glm5next'
E llama_model_load_from_file_impl: failed to load model
E cmn  common_init_: failed to load model '/.cache/huggingface/hub/models--unsloth--GLM-5.3-Flash-GGUF/snapshots/d425e572fb9686125831f476129e51cea34bc5b4/UD-Q2_K_XL/GLM-5.3-Flash-UD-Q2_K_XL-00001-of-00004.gguf'
E srv    load_model: failed to load model, '/.cache/huggingface/hub/models--unsloth--GLM-5.3-Flash-GGUF/snapshots/d425e572fb9686125831f476129e51cea34bc5b4/UD-Q2_K_XL/GLM-5.3-Flash-UD-Q2_K_XL-00001-of-00004.gguf'

Motivation

Flash should hit the best performance / size ratio, hence I would like to see it

Possible Implementation

No response

[laurentpayot]

On the way: #27754