diff --git a/pipelines/generic.py b/pipelines/generic.py
index c3fd8fd42..6ad9a3fd5 100644
--- a/pipelines/generic.py
+++ b/pipelines/generic.py
@@ -203,7 +203,8 @@ def load_text_encoder(repo_id, cls_name, load_config=None, subfolder="text_encod
         # Qwen3ForCausalLM - shared text encoders by hidden_size:
         # - Z-Image, Klein-4B: Qwen3-4B (hidden_size=2560)
         # - Klein-9B: Qwen3-8B (hidden_size=4096)
-        elif cls_name == transformers.Qwen3ForCausalLM and allow_shared and shared.opts.te_shared_t5:
+        # SDNQ repos for Klein and Z-Image contain text encoders pre-quantized with different quantization methods, skip shared loading
+        elif cls_name == transformers.Qwen3ForCausalLM and allow_shared and shared.opts.te_shared_t5 and 'sdnq' not in repo_id.lower():
             if '-9b' in repo_id.lower():
                 shared_repo = 'black-forest-labs/FLUX.2-klein-9B'  # 9B variants use Qwen3-8B
             else:
diff --git a/pipelines/model_flux2_klein.py b/pipelines/model_flux2_klein.py
index 0b6ce47e0..d810821d9 100644
--- a/pipelines/model_flux2_klein.py
+++ b/pipelines/model_flux2_klein.py
@@ -1,58 +1,23 @@
-import os
-import shutil
 import transformers
 import diffusers
 from modules import shared, devices, sd_models, model_quant, sd_hijack_te, sd_hijack_vae
 from pipelines import generic
 
 
-def ensure_tokenizer_files(checkpoint_info):
-    """Ensure tokenizer files are compatible with Transformers v4."""
-    local_path = checkpoint_info.path
-    if not os.path.isdir(local_path):
-        return
-    tokenizer_path = os.path.join(local_path, 'tokenizer')
-    if not os.path.isdir(tokenizer_path):
-        return
-
-    # Check all required files exist (v5 tokenizers may be missing these or have incompatible configs)
-    required = ['vocab.json', 'merges.txt', 'tokenizer_config.json']
-    missing = [f for f in required if not os.path.exists(os.path.join(tokenizer_path, f))]
-    if not missing:
-        return
-
-    # Download v4-compatible tokenizer files from Z-Image-Turbo
-    shared.log.debug(f'Load model: fetching v4-compatible tokenizer from Z-Image-Turbo (missing: {missing})')
-    try:
-        from huggingface_hub import hf_hub_download
-        for f in required:
-            src = hf_hub_download('Tongyi-MAI/Z-Image-Turbo', f'tokenizer/{f}', cache_dir=shared.opts.hfcache_dir)
-            shutil.copy(src, os.path.join(tokenizer_path, f))
-    except Exception as e:
-        shared.log.warning(f'Load model: failed to fetch tokenizer files: {e}')
-
-
 def load_flux2_klein(checkpoint_info, diffusers_load_config=None):
     if diffusers_load_config is None:
         diffusers_load_config = {}
     repo_id = sd_models.path_to_repo(checkpoint_info)
     sd_models.hf_auth_check(checkpoint_info)
 
-    # Ensure tokenizer files exist for models created with Transformers v5
-    ensure_tokenizer_files(checkpoint_info)
-
-    # Detect SDNQ pre-quantized repo - disable shared text encoder to use pre-quantized weights from SDNQ repo
-    is_sdnq = 'sdnq' in repo_id.lower()
-
     load_args, _quant_args = model_quant.get_dit_args(diffusers_load_config, allow_quant=False)
-    shared.log.debug(f'Load model: type=Flux2Klein repo="{repo_id}" prequant={"sdnq" if is_sdnq else "none"} config={diffusers_load_config} offload={shared.opts.diffusers_offload_mode} dtype={devices.dtype} args={load_args}')
+    shared.log.debug(f'Load model: type=Flux2Klein repo="{repo_id}" config={diffusers_load_config} offload={shared.opts.diffusers_offload_mode} dtype={devices.dtype} args={load_args}')
 
     # Load transformer - Klein uses Flux2Transformer2DModel (same class as Flux2, different size)
     transformer = generic.load_transformer(repo_id, cls_name=diffusers.Flux2Transformer2DModel, load_config=diffusers_load_config)
 
     # Load text encoder - Klein uses Qwen3 (4B for Klein-4B, 8B for Klein-9B)
-    # For SDNQ repos, disable shared text encoder to use pre-quantized weights from the repo
-    text_encoder = generic.load_text_encoder(repo_id, cls_name=transformers.Qwen3ForCausalLM, load_config=diffusers_load_config, allow_shared=not is_sdnq)
+    text_encoder = generic.load_text_encoder(repo_id, cls_name=transformers.Qwen3ForCausalLM, load_config=diffusers_load_config)
 
     pipe = diffusers.Flux2KleinPipeline.from_pretrained(
         repo_id,