ModelCloud · Qubitium · May 22, 2026 · May 22, 2026 · May 22, 2026 · May 22, 2026
diff --git a/README.md b/README.md
@@ -21,6 +21,7 @@
 
 ## Latest News
 
+* 05/21/2026 7.1.0-dev `main`: ✨ Added `nemotron_labs_diffusion` model support
 * 05/20/2026 7.1.0-dev `main`: ✨ Added `interns1`, `ovis2_5`, `ovis2_6_moe` and `ovis2_6_next` model support
 * 05/15/2026 7.1.0-dev `main`: ✨ Added `mimo_v2` model support
 * 05/13/2026 7.1.0-dev `main`: ✨ Added `minicpmv_4_6` and `DeepSeek V4` model support
@@ -247,23 +248,23 @@ Selected public references where teams or companies explicitly mention GPT-QMode
 
 ## Model Support  
 
-| Model                    |   |                                 |   |                  |   |                     |   |                         |   |
-|--------------------------|---|---------------------------------|---|------------------|---|---------------------|---|-------------------------|---|
-| Apertus                  | ✅ | EXAONE 3/4                      | ✅ | Dots1            | ✅ | Mistral3            | ✅ | Qwen 2/3/3.5 (Next/MoE) | ✅ |
-| Baichuan                 | ✅ | Falcon (H1 / Mamba)             | ✅ | InternLM 1/2/2.5 | ✅ | Mixtral             | ✅ | Qwen 2/2.5/3 VL         | ✅ |
-| Bloom                    | ✅ | FastVLM                         | ✅ | Kimi K2          | ✅ | MobileLLM           | ✅ | Qwen 2.5/3 Omni         | ✅ |
-| ChatGLM                  | ✅ | Gemma 1-4 / 3n                  | ✅ | Klear            | ✅ | MOSS                | ✅ | RefinedWeb              | ✅ |
-| CodeGen                  | ✅ | GPTBigCode                      | ✅ | LING/RING        | ✅ | MPT                 | ✅ | StableLM                | ✅ |
-| Cohere 1-2               | ✅ | GPT-Neo / NeoX                  | ✅ | Llama 1-3.3      | ✅ | Nemotron H / Omni   | ✅ | StarCoder2              | ✅ |
-| DBRX Converted           | ✅ | GPT-2                           | ✅ | Llama 3.2 VL     | ✅ | Nemotron Ultra      | ✅ | TeleChat2               | ✅ |
-| Deci                     | ✅ | GPT-J                           | ✅ | Llama 4          | ✅ | OPT                 | ✅ | Trinity                 | ✅ |
-| DeepSeek-V2/V3/V4/R1        | ✅ | GPT-OSS                         | ✅ | LongCat Flash    | ✅ | OLMo2 / LLaDA2      | ✅ | Yi                      | ✅ |
+| Model                    |   |                                 |   |                  |   |                                 |   |                         |   |
+|--------------------------|---|---------------------------------|---|------------------|---|---------------------------------|---|-------------------------|---|
+| Apertus                  | ✅ | EXAONE 3/4                      | ✅ | Dots1            | ✅ | Mistral3                        | ✅ | Qwen 2/3/3.5 (Next/MoE) | ✅ |
+| Baichuan                 | ✅ | Falcon (H1 / Mamba)             | ✅ | InternLM 1/2/2.5 | ✅ | Mixtral                         | ✅ | Qwen 2/2.5/3 VL         | ✅ |
+| Bloom                    | ✅ | FastVLM                         | ✅ | Kimi K2          | ✅ | MobileLLM                       | ✅ | Qwen 2.5/3 Omni         | ✅ |
+| ChatGLM                  | ✅ | Gemma 1-4 / 3n                  | ✅ | Klear            | ✅ | MOSS                            | ✅ | RefinedWeb              | ✅ |
+| CodeGen                  | ✅ | GPTBigCode                      | ✅ | LING/RING        | ✅ | MPT                             | ✅ | StableLM                | ✅ |
+| Cohere 1-2               | ✅ | GPT-Neo / NeoX                  | ✅ | Llama 1-3.3      | ✅ | Nemotron H / Omni               | ✅ | StarCoder2              | ✅ |
+| DBRX Converted           | ✅ | GPT-2                           | ✅ | Llama 3.2 VL     | ✅ | Nemotron Ultra / Labs-Diffusion               | ✅ | TeleChat2               | ✅ |
+| Deci                     | ✅ | GPT-J                           | ✅ | Llama 4          | ✅ | OPT                             | ✅ | Trinity                 | ✅ |
+| DeepSeek-V2/V3/V4/R1        | ✅ | GPT-OSS                         | ✅ | LongCat Flash    | ✅ | OLMo2 / LLaDA2                  | ✅ | Yi                      | ✅ |
 | DeepSeek-V2-Lite         | ✅ | Granite / Granite MoE           | ✅ | LongLLaMA        | ✅ | Ovis 1.6/2/2.5/2.6 MoE/2.6 Next | ✅ | Seed-OSS                | ✅ |
-| Dream                    | ✅ | GRIN-MoE                        | ✅ | Instella         | ✅ | Phi 1-4             | ✅ | Voxtral                 | ✅ |
-| ERNIE 4.5 / MoE / VL MoE | ✅ | GLM 4/4V/4.5V/4.6V/5/5.1/OCR/ASR | ✅ | GLM4 MoE / Lite / 4.5V MoE | ✅ | MiniCPM 3/O/V/V 4_6 | ✅ | PanGu-α                 | ✅ |
-| XVERSE                   | ✅ | Brumby                          | ✅ | Hymba            | ✅ | Mistral             | ✅ | Qwen 1/2/3/3.5          | ✅ |
-| MiniMax M2               | ✅ | AfMoE                           | ✅ | Bailing-MoE      | ✅ | LFM2-MoE            | ✅ | Marin                   | ✅ |
-| InternVL Chat            | ✅ | Laguna                          | ✅ | Mimo / Mimo V2   | ✅ | Zamba / Zamba2      | ✅ | Intern S1               | ✅  |
+| Dream                    | ✅ | GRIN-MoE                        | ✅ | Instella         | ✅ | Phi 1-4                         | ✅ | Voxtral                 | ✅ |
+| ERNIE 4.5 / MoE / VL MoE | ✅ | GLM 4/4V/4.5V/4.6V/5/5.1/OCR/ASR | ✅ | GLM4 MoE / Lite / 4.5V MoE | ✅ | MiniCPM 3/O/V/V 4_6             | ✅ | PanGu-α                 | ✅ |
+| XVERSE                   | ✅ | Brumby                          | ✅ | Hymba            | ✅ | Mistral                         | ✅ | Qwen 1/2/3/3.5          | ✅ |
+| MiniMax M2               | ✅ | AfMoE                           | ✅ | Bailing-MoE      | ✅ | LFM2-MoE                        | ✅ | Marin                   | ✅ |
+| InternVL Chat            | ✅ | Laguna                          | ✅ | Mimo / Mimo V2   | ✅ | Zamba / Zamba2                  | ✅ | Intern S1               | ✅  |
 
 Prism Bonsai GGUF checkpoints are supported for inference only through GPT-QModel's native GGUF path and internal GGUF runtime. Bonsai checkpoints load through the normal model path or repo argument and do not require the external `gguf` package. Prism model quantization is not included.
 

diff --git a/gptqmodel/models/auto.py b/gptqmodel/models/auto.py
@@ -143,6 +143,7 @@
 from .definitions.mobilellm import MobileLLMQModel  # noqa: E402
 from .definitions.moss import MossQModel  # noqa: E402
 from .definitions.mpt import MptQModel  # noqa: E402
+from .definitions.nemotron_labs_diffusion import NemotronLabsDiffusionQModel  # noqa: E402
 from .definitions.nemotron_h import NemotronHQModel  # noqa: E402
 from .definitions.nemotron_omni import NemotronOmniQModel  # noqa: E402
 from .definitions.opt import OptQModel  # noqa: E402
@@ -310,6 +311,7 @@
     "longcat_flash": LongCatFlashQModel,
     "llava_qwen2": LlavaQwen2QModel,
     "nemotron_h": NemotronHQModel,
+    "nemotron_labs_diffusion": NemotronLabsDiffusionQModel,
     "nemotronh_nano_omni_reasoning_v3": NemotronOmniQModel,
     "bailing_moe": BailingMoeQModel,
     "bailing_hybrid": BailingMoeQModel,

diff --git a/gptqmodel/models/definitions/__init__.py b/gptqmodel/models/definitions/__init__.py
@@ -60,6 +60,7 @@
 from .mobilellm import MobileLLMQModel
 from .moss import MossQModel
 from .mpt import MptQModel
+from .nemotron_labs_diffusion import NemotronLabsDiffusionQModel
 from .opt import OptQModel
 from .ovis import OvisQModel
 from .ovis2_5 import Ovis2_5QModel

diff --git a/gptqmodel/models/definitions/nemotron_labs_diffusion.py b/gptqmodel/models/definitions/nemotron_labs_diffusion.py
@@ -0,0 +1,30 @@
+# SPDX-FileCopyrightText: 2026 ModelCloud.ai
+# SPDX-License-Identifier: Apache-2.0
+
+from transformers import AutoModel
+
+from ..base import BaseQModel
+
+
+class NemotronLabsDiffusionQModel(BaseQModel):
+    require_trust_remote_code = True
+    loader = AutoModel
+
+    lm_head = "diffusion_head"
+    pre_lm_head_norm_module = "encoder.norm"
+
+    awq_scale_optimize_shape_dependent_modules = ["self_attn.o_proj"]
+
+    # Nemotron Labs Diffusion uses a custom AutoModel with an internal
+    # Ministral-style decoder stack under encoder.layers.
+    module_tree = [
+        "encoder",
+        "layers",
+        "#",
+        {
+            "input_layernorm": ("input_layernorm:!",),
+            "self_attn": ("q_proj:0", "k_proj:0", "v_proj:0", "o_proj:1"),
+            "post_attention_layernorm": ("post_attention_layernorm:!",),
+            "mlp": ("gate_proj:0", "up_proj:0", "down_proj:1"),
+        },
+    ]
diff --git a/tests/models/test_nemotron_labs_diffusion.py b/tests/models/test_nemotron_labs_diffusion.py
@@ -0,0 +1,25 @@
+# SPDX-FileCopyrightText: 2024-2025 ModelCloud.ai
+# SPDX-FileCopyrightText: 2024-2025 qubitium@modelcloud.ai
+# SPDX-License-Identifier: Apache-2.0
+# Contact: qubitium@modelcloud.ai, x.com/qubitium
+
+from model_test import ModelTest
+
+
+class TestNemotronUltra(ModelTest):
+    NATIVE_MODEL_ID = "/monster/data/model/Nemotron-Labs-Diffusion-3B" # nvidia/Nemotron-Labs-Diffusion-3B
+    # FIXME Evalution appears to be incompatible with NemoStation/Marlin-2B support; the original model's scores are also quite low.
+    # original model score: {'arc_challenge': {'accuracy,loglikelihood': 0.19795221843003413, 'accuracy,loglikelihood_norm': 0.20819112627986347}}
+    EVAL_TASKS_SLOW = {
+        "arc_challenge": {
+            "chat_template": True,
+            "acc": {"value": 0.197098976109215, "floor_pct": 0.36},
+            "acc_norm": {"value": 0.2235494880546075, "floor_pct": 0.36},
+        },
+    }
+    EVAL_TASKS_FAST = ModelTest.derive_fast_eval_tasks(EVAL_TASKS_SLOW)
+    TRUST_REMOTE_CODE = True
+    SAVE_PATH = "./temp/Nemotron-Labs-Diffusion"
+
+    def test_nemotron_ultra(self):
+        self.quantize_and_evaluate()