GLM-5.2-NVFP4-AQLM-Abliterated-Vision

FlyCockpit/GLM-5.2-NVFP4-AQLM-Abliterated-Vision

GLM-5.2-NVFP4-AQLM-Abliterated-Vision is a image-text-to-text model from FlyCockpit. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

Drop-in abliterated + vision weights for the MiaAI-Lab 3× DGX Spark recipe.

Downloads · 30 days

17% of all-time downloads

All-time downloads

175

Public

Parameters

208B

293 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors292 GB · 100%

Parameter types

How the weights are stored.

U8125B · 60%

Try a prompt

Base models

jarrelscy/GLM-5.2-NVFP4-AQLM-hybrid

Model card

From the Hugging Face model README

GLM-5.2 NVFP4+AQLM Abliterated Vision

Drop-in abliterated + vision weights for the MiaAI-Lab 3× DGX Spark recipe.

Construction

Piece	Source
Text + vision hybrid base	`jarrelscy/GLM-5.2-NVFP4-AQLM-hybrid` @ `53e0082eedebd806b63e19779c47905937d768ca`
Abliteration donor	`jacklarmer/GLM-5.2-Abliterated-MXFP8-NVFP4-NF3-Hybrid`
Method	Tensor transplant of BF16 `self_attn.o_proj.weight` for layers 13–77 (65 tensors; 62 differed from base)
Vision tower + projector	Byte-identical to the jarrelscy / Baseten vision hybrid (untouched)

No re-quantization: o_proj is BF16 [6144, 16384] on both base and donor.

Intended serve stack

Hardware: 3× NVIDIA DGX Spark (GB10 / sm_121 / aarch64)
Image: ghcr.io/miaai-lab/glm-5.2-nvfp4-triple-dgx-sparks:k12l1-vision
Launcher: MiaAI-Lab ./start.sh with MM_ENCODER_TP_MODE=data, TP=3
Playbook: https://github.com/FlyCockpit/GLM-5.2-Abliterated-Vision-3x-DGX-Sparks

Warning

This model has reduced refusal behavior relative to the stock hybrid. You are responsible for lawful use and your own evaluation.

License

Packaging Apache-2.0. Base hybrid, vision components, and upstream GLM-5.2 weights retain their original licenses/terms (see jarrelscy / DeepSeek-adjacent upstream cards). Apache-2.0 is used for this packaging where compatible with those terms.

Credits

MiaAI-Lab triple-Spark recipe
jarrelscy NVFP4+AQLM hybrid + vision graft
jacklarmer abliterated donor
Baseten / community MoonViT vision path

Task: Image-Text-to-Text
Type: glm5v
License: apache-2.0
Created: Aug 4, 2026
Updated: Aug 4, 2026