Running flux kontext q2 quantitative model is crashing

[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2025-06-28 20:15:16.232
** Platform: Windows
** Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr 2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
** Python executable: C:\ziyong\ComfyUI-aki-v1.7\python\python.exe
** ComfyUI Path: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI
** ComfyUI Base Folder Path: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI
** User directory: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\user
** ComfyUI-Manager config path: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\user\default\ComfyUI-Manager\config.ini
** Log path: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-Easy-Use
12.6 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-manager

Checkpoint files will always be loaded safely.
Total VRAM 8151 MB, total RAM 15653 MB
pytorch version: 2.7.0+cu128
xformers version: 0.0.30
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5060 Laptop GPU : cudaMallocAsync
Using sage attention
Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr 2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
ComfyUI version: 0.3.42
ComfyUI frontend version: 1.23.4
[Prompt Server] web root: C:\ziyong\ComfyUI-aki-v1.7\python\Lib\site-packages\comfyui_frontend_package\static
[AnimateDiffEvo] - ERROR - No motion models found. Please download one and place in: ['C:\\ziyong\\ComfyUI-aki-v1.7\\ComfyUI\\custom_nodes\\comfyui-animatediff-evolved\\models', 'C:\\ziyong\\ComfyUI-aki-v1.7\\ComfyUI\\models\\animatediff_models']
[Crystools INFO] Crystools version: 1.25.1
[Crystools INFO] Platform release: 10
[Crystools INFO] JETSON: Not detected.
[Crystools INFO] CPU: AMD Ryzen 7 H 260 w/ Radeon 780M Graphics - Arch: AMD64 - OS: Windows 10
[Crystools INFO] pynvml (NVIDIA) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce RTX 5060 Laptop GPU
[Crystools INFO] NVIDIA Driver: 576.80
[ComfyUI-Easy-Use] server: v1.3.1 Loaded
[ComfyUI-Easy-Use] web root: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-Easy-Use\web_version/v2 Loaded
ComfyUI-GGUF: Partial torch compile only, consider updating pytorch
### Loading: ComfyUI-Impact-Pack (V8.17.1)
[WARN] ComfyUI-Impact-Pack: custom_wildcards path not found: C:\_a\comfyui-aki-v1.6\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\custom_wildcards. Using default path.
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Inspire-Pack (V1.20)
### Loading: ComfyUI-Manager (V3.33.3)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] Since --preview-method is set, ComfyUI-Manager's preview method feature will be ignored.
### ComfyUI Version: v0.3.42-1-gbd951a71 | Released on '2025-06-26'
======================================== ComfyUI-nunchaku Initialization ========================================
Nunchaku version: 0.3.1
ComfyUI-nunchaku version: 0.3.2
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
C:\ziyong\ComfyUI-aki-v1.7\python\Lib\site-packages\albumentations\__init__.py:28: UserWarning: A new version of Albumentations is available: '2.0.8' (you have '2.0.3'). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
check_for_updates()
Please 'pip install apex'
=================================================================================================================
(pysssss:WD14Tagger) [DEBUG] Available ORT providers: TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
Workspace manager - Openning file hash dict
🦄🦄Loading: Workspace Manager (V2.1.0)
[C:\ziyong\ComfyUI-aki-v1_x_7\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[C:\ziyong\ComfyUI-aki-v1_x_7\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
[C:\ziyong\ComfyUI-aki-v1_x_7\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
DWPose: Onnxruntime with acceleration providers detected
LIGER kernel not found. The option to enable it will be disabled.
JoyCaptionBetaOne (JCBO.py) nodes (Full, Simple, ExtraOptions) loaded with refined quantization.
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\pr-was-node-suite-comfyui-47064894\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 220 nodes successfully.

"Art is the most intense mode of individualism that the world has known." - Oscar Wilde

[rgthree-comfy] Loaded 47 exciting nodes. 🎉

WeiLin-Comfyui-Tools ==> 所有依赖项已安装。
======== WeiLin插件服务已启动 ========
======== WeiLin Server Init ========

Import times for custom nodes:
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\sd-dynamic-thresholding
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-WD14-Tagger
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\AIGODLIKE-COMFYUI-TRANSLATION
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-get-meta
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-GGUF
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-layerdiffuse
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui_ipadapter_plus
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-custom-scripts
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui_UltimateSDUpscale
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui_essentials
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\Comfyui_JC2
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-FramePackWrapper_Plus
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-advanced-controlnet
0.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-KJNodes
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI_ExtraModels
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-animatediff-evolved
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-Inspire-Pack
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\efficiency-nodes-comfyui
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui_controlnet_aux
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\WeiLin-Comfyui-Tools
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-workspace-manager
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-HunyuanVideoWrapper
0.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-Impact-Pack
0.3 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-LogicUtils
0.3 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI_TensorRT
0.4 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-VideoHelperSuite
0.7 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-crystools
1.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\rgthree-comfy
1.5 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\comfyui-manager
1.6 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-nunchaku
2.1 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\ComfyUI-Easy-Use
6.0 seconds: C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\pr-was-node-suite-comfyui-47064894

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://127.0.0.1:8188
C:\ziyong\ComfyUI-aki-v1.7\ComfyUI\custom_nodes\WeiLin-Comfyui-Tools\app\server\translate\api_translate.py:59: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
import pkg_resources
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
got prompt
Using xformers attention in VAE
Using xformers attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load AutoencodingEngine
loaded completely 658.46875 159.87335777282715 True
Using scaled fp8: fp8 matrix mult: False, scale input: False
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
clip missing: ['text_projection.weight']
Requested to load FluxClipModel_
loaded completely 5395.778515625 4903.231597900391 True
1 models unloaded.
gguf qtypes: F32 (466), Q2_K (304), BF16 (10)
model weight dtype torch.bfloat16, manual cast: None
model_type FLUX
Requested to load Flux
loaded completely 4821.266919891357 3873.201416015625 True
'sm_120' is not a recognized processor for this target (ignoring processor)
'sm_120' is not a recognized processor for this target (ignoring processor)
'sm_120' is not a recognized processor for this target (ignoring processor)
'sm_120' is not a recognized processor for this target (ignoring processor)
'sm_120' is not a recognized processor for this target (ignoring processor)
'sm_120' is not a recognized processor for this target (ignoring processor)
LLVM ERROR: Cannot select: intrinsic %llvm.nvvm.shfl.sync.bfly.i32

--------
[The program exited abnormally with the exit code 3 (0x00000003)]
I am using flux kontext q2 quantization. I see that many people on the Internet can produce images normally using graphics cards with 8g of video memory. What is the cause of the crash?