From 203e46af0cbecef62f36062bfa7da4480053b309 Mon Sep 17 00:00:00 2001
From: Vladimir Mandic <mandic00@live.com>
Date: Sat, 25 Oct 2025 12:18:52 -0400
Subject: [PATCH] update reference sizes

Signed-off-by: Vladimir Mandic <mandic00@live.com>
---
 cli/hf-search.py     | 16 ++++++++--------
 html/reference.json  | 13 +++++++++----
 pipelines/generic.py |  9 +++++++++
 3 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/cli/hf-search.py b/cli/hf-search.py
index f69c215eb..9ee696602 100755
--- a/cli/hf-search.py
+++ b/cli/hf-search.py
@@ -7,12 +7,12 @@ from rich import print # pylint: disable=redefined-builtin
 if __name__ == "__main__":
     sys.argv.pop(0)
     keyword = sys.argv[0] if len(sys.argv) > 0 else ''
+    hf.logging.set_verbosity_info()
     hf_api = hf.HfApi()
-    model_filter = hf.ModelFilter(
-        model_name=keyword,
-        # task='text-to-image',
-        library=['diffusers'],
-    )
-    res = hf_api.list_models(filter=model_filter, full=True, limit=50, sort="downloads", direction=-1)
-    models = [{ 'name': m.id, 'downloads': m.downloads, 'mtime': m.lastModified, 'url': f'https://huggingface.co/{m.id}', 'pipeline': m.pipeline_tag, 'tags': m.tags } for m in res]
-    print(models)
+    res = hf_api.list_models(model_name=keyword, full=True, limit=100, sort="downloads", direction=-1)
+    res = sorted(res, key=lambda x: x.id)
+    for m in res:
+        meta = hf_api.model_info(m.id, files_metadata=True)
+        m.files = [f.rfilename for f in meta.siblings if f.rfilename.endswith('.bin') or f.rfilename.endswith('.safetensors')]
+        m.size = sum([f.size for f in meta.siblings]) / 1024 / 1024 / 1024 # in GB
+        print({ 'name': m.id, 'files': len(m.files), 'size': m.size, 'downloads': m.downloads, 'mtime': m.lastModified, 'url': f'https://huggingface.co/{m.id}', 'pipeline': m.pipeline_tag })
diff --git a/html/reference.json b/html/reference.json
index 2022a40db..437e7461c 100644
--- a/html/reference.json
+++ b/html/reference.json
@@ -912,7 +912,7 @@
     "desc": "4 bit (UINT4 with SVD rank 32) quantization of black-forest-labs/FLUX.1-dev using SDNQ.",
     "skip": true,
     "tags": "quantized",
-    "size": 6.8,
+    "size": 13.53,
     "date": "2025 October",
     "extras": ""
   },
@@ -922,7 +922,7 @@
     "desc": "quantization of lodestones/Chroma1-HD using SDNQ: sdnq-svd 4-bit uint with svd rank 32",
     "skip": true,
     "tags": "quantized",
-    "size": 5.4,
+    "size": 11.89,
     "date": "2025 October",
     "extras": ""
   },
@@ -933,6 +933,7 @@
     "skip": true,
     "tags": "quantized",
     "date": "2025 October",
+    "size": 23.54,
     "extras": ""
   },
   "Wan-AI Wan2.2 A14B I2I sdnq-svd-uint4": {
@@ -942,6 +943,7 @@
     "skip": true,
     "tags": "quantized",
     "date": "2025 October",
+    "size": 23.55,
     "extras": ""
   },
   "Qwen-Image sdnq-svd-uint4": {
@@ -951,6 +953,7 @@
     "skip": true,
     "tags": "quantized",
     "date": "2025 October",
+    "size": 16.09,
     "extras": ""
   },
   "Qwen-Image-Edit sdnq-svd-uint4": {
@@ -960,6 +963,7 @@
     "skip": true,
     "tags": "quantized",
     "date": "2025 October",
+    "size": 16.10,
     "extras": ""
   },
   "Qwen-Image-Edit-2509 sdnq-svd-uint4": {
@@ -969,6 +973,7 @@
     "skip": true,
     "tags": "quantized",
     "date": "2025 October",
+    "size": 16.10,
     "extras": ""
   },
 
@@ -978,7 +983,7 @@
     "desc": "quantization of Laxhar/noobai-XL-1.1 using SDNQ: sdnq-svd 4-bit uint with svd rank 128",
     "skip": true,
     "tags": "quantized",
-    "size": 2.56,
+    "size": 3.37,
     "date": "2025 October",
     "extras": ""
   },
@@ -988,7 +993,7 @@
     "desc": "quantization of Laxhar/noobai-XL-Vpred-1.0 using SDNQ: sdnq-svd 4-bit uint with svd rank 128",
     "skip": true,
     "tags": "quantized",
-    "size": 2.56,
+    "size": 3.37,
     "date": "2025 October",
     "extras": ""
   },
diff --git a/pipelines/generic.py b/pipelines/generic.py
index e78ac7b8b..70f3b4449 100644
--- a/pipelines/generic.py
+++ b/pipelines/generic.py
@@ -49,6 +49,8 @@ def load_transformer(repo_id, cls_name, load_config={}, subfolder="transformer",
             )
         else:
             shared.log.debug(f'Load model: transformer="{repo_id}" cls={cls_name.__name__} subfolder={subfolder} quant="{quant_type}" args={load_args}')
+            if 'sdnq-' in repo_id.lower():
+                quant_args = {}
             if dtype is not None:
                 load_args['torch_dtype'] = dtype
             if subfolder is not None:
@@ -131,6 +133,13 @@ def load_text_encoder(repo_id, cls_name, load_config={}, subfolder="text_encoder
                 )
                 text_encoder.quantization_method = 'SVDQuant'
             elif shared.opts.te_shared_t5:
+                """                
+                if 'sdnq-' in repo_id.lower():
+                    repo_id = 'Disty0/FLUX.1-dev-SDNQ-uint4-svd-r32'
+                    load_args['subfolder'] = 'text_encoder_2'
+                    quant_args = {}
+                else:
+                """
                 repo_id = 'Disty0/t5-xxl'
                 shared.log.debug(f'Load model: text_encoder="{repo_id}" cls={cls_name.__name__} quant="{quant_type}" shared={shared.opts.te_shared_t5}')
                 if dtype is not None: