INFO:hf-to-gguf:Loading model: Qwen3.6-35B-A3B-DFlash
INFO:hf-to-gguf:Model architecture: DFlashDraftModel
INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:fc.weight,                torch.bfloat16 --> BF16, shape = {10240, 2048}
INFO:hf-to-gguf:hidden_norm.weight,       torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.0.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.0.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.0.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.0.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.0.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.0.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.0.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.0.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.0.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.0.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.1.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.1.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.1.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.1.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.1.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.1.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.1.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.2.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.2.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.2.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.2.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.2.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.2.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.2.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.3.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.3.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.3.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.3.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.3.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.3.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.3.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.4.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.4.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.4.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.4.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.4.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.4.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.4.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.4.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.4.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.5.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.5.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.5.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.5.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.5.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.5.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.5.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.6.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.6.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.6.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.6.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.6.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.6.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.6.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.attn_norm.weight,   torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.ffn_down.weight,    torch.bfloat16 --> BF16, shape = {6144, 2048}
INFO:hf-to-gguf:blk.7.ffn_gate.weight,    torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.7.ffn_up.weight,      torch.bfloat16 --> BF16, shape = {2048, 6144}
INFO:hf-to-gguf:blk.7.ffn_norm.weight,    torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.7.attn_k.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.7.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.7.attn_q.weight,      torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.7.attn_v.weight,      torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:output_norm.weight,       torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 262144
INFO:hf-to-gguf:gguf: embedding length = 2048
INFO:hf-to-gguf:gguf: feed forward length = 6144
INFO:hf-to-gguf:gguf: head count = 32
INFO:hf-to-gguf:gguf: key-value head count = 4
INFO:hf-to-gguf:gguf: rope scaling type = YARN
INFO:hf-to-gguf:gguf: rope theta = 10000000
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: file type = 32
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
INFO:hf-to-gguf:DFLASH: Using tokenizer from target model: ..\Qwen3.6-35B-A3B
You are using a model of type qwen3_5_moe to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
INFO:gguf.vocab:Adding 247587 merge(s).
INFO:gguf.vocab:Setting special token type eos to 248046
INFO:gguf.vocab:Setting special token type pad to 248044
INFO:gguf.vocab:Setting special token type bos to 248044
INFO:gguf.vocab:Setting add_bos_token to False
INFO:gguf.vocab:Setting chat_template to {%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
    {%- if content is string %}
        {{- content }}
    {%- elif content is iterable and content is not mapping %}
        {%- for item in content %}
            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
                {%- if is_system_content %}
                    {{- raise_exception('System message cannot contain images.') }}
                {%- endif %}
                {%- if do_vision_count %}
                    {%- set image_count.value = image_count.value + 1 %}
                {%- endif %}
                {%- if add_vision_id %}
                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
                {%- endif %}
                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
            {%- elif 'video' in item or item.type == 'video' %}
                {%- if is_system_content %}
                    {{- raise_exception('System message cannot contain videos.') }}
                {%- endif %}
                {%- if do_vision_count %}
                    {%- set video_count.value = video_count.value + 1 %}
                {%- endif %}
                {%- if add_vision_id %}
                    {{- 'Video ' ~ video_count.value ~ ': ' }}
                {%- endif %}
                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
            {%- elif 'text' in item %}
                {{- item.text }}
            {%- else %}
                {{- raise_exception('Unexpected item type in content.') }}
            {%- endif %}
        {%- endfor %}
    {%- elif content is none or content is undefined %}
        {{- '' }}
    {%- else %}
        {{- raise_exception('Unexpected content type.') }}
    {%- endif %}
{%- endmacro %}
{%- if not messages %}
    {{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
    {{- '<|im_start|>system\n' }}
    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
    {%- for tool in tools %}
        {{- "\n" }}
        {{- tool | tojson }}
    {%- endfor %}
    {{- "\n</tools>" }}
    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
    {%- if messages[0].role == 'system' %}
        {%- set content = render_content(messages[0].content, false, true)|trim %}
        {%- if content %}
            {{- '\n\n' + content }}
        {%- endif %}
    {%- endif %}
    {{- '<|im_end|>\n' }}
{%- else %}
    {%- if messages[0].role == 'system' %}
        {%- set content = render_content(messages[0].content, false, true)|trim %}
        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
    {%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
    {%- set index = (messages|length - 1) - loop.index0 %}
    {%- if ns.multi_step_tool and message.role == "user" %}
        {%- set content = render_content(message.content, false)|trim %}
        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
            {%- set ns.multi_step_tool = false %}
            {%- set ns.last_query_index = index %}
        {%- endif %}
    {%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
    {{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
    {%- set content = render_content(message.content, true)|trim %}
    {%- if message.role == "system" %}
        {%- if not loop.first %}
            {{- raise_exception('System message must be at the beginning.') }}
        {%- endif %}
    {%- elif message.role == "user" %}
        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
    {%- elif message.role == "assistant" %}
        {%- set reasoning_content = '' %}
        {%- if message.reasoning_content is string %}
            {%- set reasoning_content = message.reasoning_content %}
        {%- else %}
            {%- if '</think>' in content %}
                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
            {%- endif %}
        {%- endif %}
        {%- set reasoning_content = reasoning_content|trim %}
        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
        {%- else %}
            {{- '<|im_start|>' + message.role + '\n' + content }}
        {%- endif %}
        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
            {%- for tool_call in message.tool_calls %}
                {%- if tool_call.function is defined %}
                    {%- set tool_call = tool_call.function %}
                {%- endif %}
                {%- if loop.first %}
                    {%- if content|trim %}
                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
                    {%- else %}
                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
                    {%- endif %}
                {%- else %}
                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
                {%- endif %}
                {%- if tool_call.arguments is defined %}
                    {%- for args_name, args_value in tool_call.arguments|items %}
                        {{- '<parameter=' + args_name + '>\n' }}
                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
                        {{- args_value }}
                        {{- '\n</parameter>\n' }}
                    {%- endfor %}
                {%- endif %}
                {{- '</function>\n</tool_call>' }}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- elif message.role == "tool" %}
        {%- if loop.previtem and loop.previtem.role != "tool" %}
            {{- '<|im_start|>user' }}
        {%- endif %}
        {{- '\n<tool_response>\n' }}
        {{- content }}
        {{- '\n</tool_response>' }}
        {%- if not loop.last and loop.nextitem.role != "tool" %}
            {{- '<|im_end|>\n' }}
        {%- elif loop.last %}
            {{- '<|im_end|>\n' }}
        {%- endif %}
    {%- else %}
        {{- raise_exception('Unexpected message role.') }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|im_start|>assistant\n' }}
    {%- if enable_thinking is defined and enable_thinking is false %}
        {{- '<think>\n\n</think>\n\n' }}
    {%- else %}
        {{- '<think>\n' }}
    {%- endif %}
{%- endif %}
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:..\Qwen3.6-35B-A3B-DFlash\Qwen3.6-35B-A3B-DFlash-bf16.gguf: n_tensors = 91, total_size = 948.1M
Writing: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 948M/948M [00:05<00:00, 188Mbyte/s]
INFO:hf-to-gguf:Model successfully exported to ..\Qwen3.6-35B-A3B-DFlash\Qwen3.6-35B-A3B-DFlash-bf16.gguf