Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,300 @@
+---
+tags:
+- fp4
+- vllm
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+pipeline_tag: text-generation
+license: apache-2.0
+base_model: Qwen/Qwen3-VL-235B-A22B-Instruct
+---
+
+# Qwen3-VL-235B-A22B-Instruct-NVFP4
+
+## Model Overview
+- **Model Architecture:** Qwen/Qwen3-VL-235B-A22B-Instruct
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** FP4
+  - **Activation quantization:** FP4
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
+- **Release Date:** 10/29/2025
+- **Version:** 1.0
+- **Model Developers:** RedHatAI
+
+This model is a quantized version of [Qwen/Qwen3-VL-235B-A22B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct).
+It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model.
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights and activations of [Qwen/Qwen3-VL-235B-A22B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct) to FP4 data type, ready for inference with vLLM>=0.9.1
+This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.
+
+Only the weights and activations of the linear operators within transformers blocks are quantized using [LLM Compressor](https://github.com/vllm-project/llm-compressor).
+
+## Deployment
+
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model_id = "RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4"
+number_gpus = 1
+
+sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+
+llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
+
+outputs = llm.generate(prompts, sampling_params)
+
+generated_text = outputs[0].outputs[0].text
+print(generated_text)
+```
+
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+This model was created by applying [LLM Compressor with calibration samples from UltraChat](https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_w4a4_fp4/llama3_example.py), as presented in the code snipet below.
+
+<details>
+  
+```python
+import torch
+from datasets import load_dataset
+from transformers import AutoProcessor, Qwen3VLMoeForConditionalGeneration
+
+from llmcompressor import oneshot
+from llmcompressor.modeling import replace_modules_for_calibration
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.utils import dispatch_for_generation
+
+# NOTE: Requires a minimum of transformers 4.57.0
+
+MODEL_ID = "Qwen/Qwen3-VL-235B-A22B-Instruct"
+
+
+# Load model.
+model = Qwen3VLMoeForConditionalGeneration.from_pretrained(MODEL_ID, torch_dtype="auto")
+processor = AutoProcessor.from_pretrained(MODEL_ID)
+model = replace_modules_for_calibration(model)
+
+DATASET_ID = "neuralmagic/calibration"
+NUM_CALIBRATION_SAMPLES = 20
+MAX_SEQUENCE_LENGTH = 8192
+
+ds = load_dataset(DATASET_ID, name="LLM", split=f"train[:{NUM_CALIBRATION_SAMPLES}]")
+
+
+def preprocess_function(example):
+    messgages = []
+    for message in example["messages"]:
+        messgages.append(
+            {
+                "role": message["role"],
+                "content": [{"type": "text", "text": message["content"]}],
+            }
+        )
+
+    return processor.apply_chat_template(
+        messgages,
+        return_tensors="pt",
+        padding=False,
+        truncation=True,
+        max_length=MAX_SEQUENCE_LENGTH,
+        tokenize=True,
+        add_special_tokens=False,
+        return_dict=True,
+        add_generation_prompt=False,
+    )
+
+
+ds = ds.map(preprocess_function, batched=False, remove_columns=ds.column_names)
+
+
+def data_collator(batch):
+    assert len(batch) == 1
+    return {
+        key: (
+            torch.tensor(value)
+            if key != "pixel_values"
+            else torch.tensor(value, dtype=torch.bfloat16).squeeze(0)
+        )
+        for key, value in batch[0].items()
+    }
+
+
+# Configure the quantization algorithm and scheme.
+# In this case, we:
+#   * quantize the weights to fp4 with group-wise quantization
+#   * quantize the activations to fp4 with dynamic group activations
+recipe = QuantizationModifier(
+    targets="Linear",
+    scheme="NVFP4",
+    ignore=[
+        "re:.*lm_head",
+        "re:visual.*",
+        "re:model.visual.*",
+        "re:.*mlp.gate$",
+    ],
+)
+
+# Apply quantization.
+oneshot(
+    model=model,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+    dataset=ds,
+    data_collator=data_collator,
+)
+
+print("========== SAMPLE GENERATION ==============")
+dispatch_for_generation(model)
+input_ids = processor(text="Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=20)
+print(processor.decode(output[0]))
+print("==========================================")
+
+
+# Save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.rstrip("/").split("/")[-1] + "-NVFP4"
+model.save_pretrained(SAVE_DIR)
+processor.save_pretrained(SAVE_DIR)
+
+```
+</details>
+
+## Evaluation
+
+This model was evaluated on the well-known OpenLLM v1, OpenLLM v2 and HumanEval_64 benchmarks using [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness). The Reasoning evals were done using [ligheval](https://github.com/neuralmagic/lighteval).
+
+### Accuracy
+<table>
+  <thead>
+    <tr>
+      <th>Category</th>
+      <th>Metric</th>
+      <th>Qwen/Qwen3-VL-235B-A22B-Instruct</th>
+      <th>RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4 (this model)</th>
+      <th>Recovery</th>
+    </tr>
+  </thead>
+  <tbody>
+    <!-- OpenLLM -->
+    <tr>
+      <td rowspan="7"><b>OpenLLM</b></td>
+      <td>arc_challenge</td>
+      <td>72.95</td>
+      <td>71.59</td>
+      <td>98.13</td>
+    </tr>
+    <tr>
+      <td>gsm8k</td>
+      <td>90.37</td>
+      <td>88.25</td>
+      <td>97.65</td>
+    </tr>
+    <tr>
+      <td>hellaswag</td>
+      <td>87.94</td>
+      <td>86.80</td>
+      <td>98.70</td>
+    </tr>
+    <tr>
+      <td>mmlu</td>
+      <td>87.12</td>
+      <td>86.22</td>
+      <td>98.97</td>
+    </tr>
+    <tr>
+      <td>truthfulqa_mc2</td>
+      <td>63.31</td>
+      <td>62.37</td>
+      <td>98.52</td>
+    </tr>
+    <tr>
+      <td>winogrande</td>
+      <td>81.93</td>
+      <td>80.43</td>
+      <td>98.17</td>
+    </tr>
+    <tr>
+      <td><b>Average</b></td>
+      <td><b>80.60</b></td>
+      <td><b>79.28</b></td>
+      <td><b>98.35</b></td>
+    </tr>
+    <!-- Vision -->
+    <tr>
+      <td rowspan="7"><b>Vision</b></td>
+      <td>mmmu_val</td>
+      <td>63.56</td>
+      <td>62.11</td>
+      <td>97.71</td>
+    </tr>
+    <tr>
+      <td>chartqa</td>
+      <td>90.52</td>
+      <td>89.00</td>
+      <td>98.32</td>
+    </tr>
+    <tr>
+      <td><b>Average</b></td>
+      <td><b>77.04</b></td>
+      <td><b>75.56</b></td>
+      <td><b>98.08</b></td>
+    </tr>
+  </tbody>
+</table>
+
+
+
+### Reproduction
+
+The results were obtained using the following commands:
+
+<details>
+
+#### OpenLLM 
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4",dtype=auto,max_model_len=4096,tensor_parallel_size=2,enable_chunked_prefill=True,enforce_eager=True\
+  --apply_chat_template \
+  --fewshot_as_multiturn \
+  --tasks openllm \
+  --batch_size auto
+```
+
+#### Vision
+```
+python3 -m lmms_eval \
+    --model vllm \
+    --model_args model=RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4,tensor_parallel_size=4,max_model_len=20000 \
+    --tasks chartqa,mmmu_val \
+    --batch_size 1
+```
+
+</details>

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,326 @@
+{
+  "architectures": [
+    "Qwen3VLMoeForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl_moe",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "nvfp4-pack-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.visual.deepstack_merger_list.0.linear_fc1",
+      "model.visual.deepstack_merger_list.0.linear_fc2",
+      "model.visual.deepstack_merger_list.1.linear_fc1",
+      "model.visual.deepstack_merger_list.1.linear_fc2",
+      "model.visual.deepstack_merger_list.2.linear_fc1",
+      "model.visual.deepstack_merger_list.2.linear_fc2",
+      "model.language_model.layers.0.mlp.gate",
+      "model.language_model.layers.1.mlp.gate",
+      "model.language_model.layers.2.mlp.gate",
+      "model.language_model.layers.3.mlp.gate",
+      "model.language_model.layers.4.mlp.gate",
+      "model.language_model.layers.5.mlp.gate",
+      "model.language_model.layers.6.mlp.gate",
+      "model.language_model.layers.7.mlp.gate",
+      "model.language_model.layers.8.mlp.gate",
+      "model.language_model.layers.9.mlp.gate",
+      "model.language_model.layers.10.mlp.gate",
+      "model.language_model.layers.11.mlp.gate",
+      "model.language_model.layers.12.mlp.gate",
+      "model.language_model.layers.13.mlp.gate",
+      "model.language_model.layers.14.mlp.gate",
+      "model.language_model.layers.15.mlp.gate",
+      "model.language_model.layers.16.mlp.gate",
+      "model.language_model.layers.17.mlp.gate",
+      "model.language_model.layers.18.mlp.gate",
+      "model.language_model.layers.19.mlp.gate",
+      "model.language_model.layers.20.mlp.gate",
+      "model.language_model.layers.21.mlp.gate",
+      "model.language_model.layers.22.mlp.gate",
+      "model.language_model.layers.23.mlp.gate",
+      "model.language_model.layers.24.mlp.gate",
+      "model.language_model.layers.25.mlp.gate",
+      "model.language_model.layers.26.mlp.gate",
+      "model.language_model.layers.27.mlp.gate",
+      "model.language_model.layers.28.mlp.gate",
+      "model.language_model.layers.29.mlp.gate",
+      "model.language_model.layers.30.mlp.gate",
+      "model.language_model.layers.31.mlp.gate",
+      "model.language_model.layers.32.mlp.gate",
+      "model.language_model.layers.33.mlp.gate",
+      "model.language_model.layers.34.mlp.gate",
+      "model.language_model.layers.35.mlp.gate",
+      "model.language_model.layers.36.mlp.gate",
+      "model.language_model.layers.37.mlp.gate",
+      "model.language_model.layers.38.mlp.gate",
+      "model.language_model.layers.39.mlp.gate",
+      "model.language_model.layers.40.mlp.gate",
+      "model.language_model.layers.41.mlp.gate",
+      "model.language_model.layers.42.mlp.gate",
+      "model.language_model.layers.43.mlp.gate",
+      "model.language_model.layers.44.mlp.gate",
+      "model.language_model.layers.45.mlp.gate",
+      "model.language_model.layers.46.mlp.gate",
+      "model.language_model.layers.47.mlp.gate",
+      "model.language_model.layers.48.mlp.gate",
+      "model.language_model.layers.49.mlp.gate",
+      "model.language_model.layers.50.mlp.gate",
+      "model.language_model.layers.51.mlp.gate",
+      "model.language_model.layers.52.mlp.gate",
+      "model.language_model.layers.53.mlp.gate",
+      "model.language_model.layers.54.mlp.gate",
+      "model.language_model.layers.55.mlp.gate",
+      "model.language_model.layers.56.mlp.gate",
+      "model.language_model.layers.57.mlp.gate",
+      "model.language_model.layers.58.mlp.gate",
+      "model.language_model.layers.59.mlp.gate",
+      "model.language_model.layers.60.mlp.gate",
+      "model.language_model.layers.61.mlp.gate",
+      "model.language_model.layers.62.mlp.gate",
+      "model.language_model.layers.63.mlp.gate",
+      "model.language_model.layers.64.mlp.gate",
+      "model.language_model.layers.65.mlp.gate",
+      "model.language_model.layers.66.mlp.gate",
+      "model.language_model.layers.67.mlp.gate",
+      "model.language_model.layers.68.mlp.gate",
+      "model.language_model.layers.69.mlp.gate",
+      "model.language_model.layers.70.mlp.gate",
+      "model.language_model.layers.71.mlp.gate",
+      "model.language_model.layers.72.mlp.gate",
+      "model.language_model.layers.73.mlp.gate",
+      "model.language_model.layers.74.mlp.gate",
+      "model.language_model.layers.75.mlp.gate",
+      "model.language_model.layers.76.mlp.gate",
+      "model.language_model.layers.77.mlp.gate",
+      "model.language_model.layers.78.mlp.gate",
+      "model.language_model.layers.79.mlp.gate",
+      "model.language_model.layers.80.mlp.gate",
+      "model.language_model.layers.81.mlp.gate",
+      "model.language_model.layers.82.mlp.gate",
+      "model.language_model.layers.83.mlp.gate",
+      "model.language_model.layers.84.mlp.gate",
+      "model.language_model.layers.85.mlp.gate",
+      "model.language_model.layers.86.mlp.gate",
+      "model.language_model.layers.87.mlp.gate",
+      "model.language_model.layers.88.mlp.gate",
+      "model.language_model.layers.89.mlp.gate",
+      "model.language_model.layers.90.mlp.gate",
+      "model.language_model.layers.91.mlp.gate",
+      "model.language_model.layers.92.mlp.gate",
+      "model.language_model.layers.93.mlp.gate",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.12.3.dev8+gdf6fd15.d20251014"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_vl_moe_text",
+    "moe_intermediate_size": 1536,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 94,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "router_aux_loss_coef": 0.001,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl_moe",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.0"
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7822beadabce2cad8d4584f01a2f51a56a47685610d4158bc335362b6b894b91
+size 4999939440

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1845e6a0f4c5ca9ffe41f1dbbb1b8216a756ff831bd3de674eb49d770bfcff
+size 4999665504

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddd29da8c5094ef629e888899ee1563b88468247816c1c9f487297db0444e14
+size 5000570208

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da0594e03d3844cae7537a8fb6f993331840f800be3b7269c26ed38a535b32c
+size 5000062648

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3104c856540779ea9f29deee3f20e918cb47225a4eb98ac27d9ca64f3ca086ef
+size 4999671160

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5112c8282c958fa2860d386faa8bf455687ab530293de03ecf01ddfa5d5169
+size 5000575440

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff9c7b937458351a128a86785bd6f07eadf75da5d3f6166659edcf35634b951
+size 5000064536

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c033a09e28c4638b67480e3b8624d15019ec837625d7576536a66bd3eaaf8f66
+size 5000575544

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf9e7f4204fd7ceb086bcc5876852e988166cd6668282c30c91aa6b016228be
+size 5000064432

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb97848ea4b65ab6617ef632b0959d7a9d09a78440e294a3bfe2f5158a18eb2c
+size 5000575768

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e8849f7b59cdabd4b0e4874d1d209cedc75f1759edf8f51bd4ff8f1a426d3
+size 5000064200

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e34b7ccc07ae5c79e0ab27ef50c449a32717b11ea0a3b1b998a021641739b0
+size 4999671168

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974e52e6316bae117c173ba1de2abe721fd3754df874fcaf46606353670cbb6b
+size 5000575448

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f044e2cee7f1bfaaad6885ca864e0d0e24c949368e5cf1b244adfa8f600406
+size 5000064528

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70bab4c1d7ac97438b9c4d0214af89e8b794e468d44dbb4baf19f4026aaff86f
+size 5000575536

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10cdf6cf4c022710ba5410caa50cad4cd694784c8dcf7a060c7f704ccaccac81
+size 5000064440

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfa55eb279b68c79eb38bd511261fef803ad8daa691ceea00851dd9ff9d54b9
+size 5000575760

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ba7af46cca6613c9444d669f676b066d58b80007265c222f7de5dcf065d4b3
+size 5000064216

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6659ac2e4699faa1bcabee5b2ca4bf93ad128ccd6eb01c9bf9ce2dea180d2c40
+size 4999671168

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f97534e90a27902601f3fd4374c52300762481cae02e582da38511a16647b74
+size 5000575440

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c55204018537b303caa83928425e56a09eb5c2317e7f4fcd2bf10b318bd8fe7
+size 5000064528

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1320d5d20e10aa9d8d24c0bc348689c64f629118f910dfa6fab4f11363e01ac
+size 5000575528

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140fe7ab1694e5c289db7368b7d0ed6ab65ee037d9667f0e6481e358373e26c9
+size 5000064440

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce01545aebdfbd9be914eecfda31416bc6c2e06164e2abceb7a3f18e3e18ad9
+size 5000575752

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99823e4f2e57e4c728673201d22241398372d9d86e546f2d92924d3a56d36542
+size 5000064224

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5f145277a3ed16ee2cae8935d504c5b278965531a7aa1f62cb931e04df01df
+size 4999671160

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0fb6e92b589abbf9ec8127ae6fdf51eea7712c61b64f085fd0618734f9fe1e
+size 4025387208

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93db8efcfef1d92475e220e0b35fc7c66913b9abec01a58c27fcd39cadf85d93
+size 1244659840

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2497b9e4c7abb83b568ce1ca10b5b903b57dcedb533128aaa0ed90d513202c1
+size 16821720

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

recipe.yaml

@@ -0,0 +1,6 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: ['re:.*lm_head', 're:visual.*', 're:model.visual.*', 're:.*mlp.gate$']
+      scheme: NVFP4

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a69a7b1f8af6d6abf8709b25d51a33d11752da7633c7e065affe8497cb5782
+size 11422755

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}