Upload merged Helios Lynx 1.0 MLX checkpoint

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

MTPLX_PUBLISH_MANIFEST.json

@@ -0,0 +1,175 @@
+{
+  "created_at": "2026-05-03T16:59:16.607393+00:00",
+  "files": [
+    {
+      "materialization": "clonefile",
+      "name": "chat_template.jinja",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/chat_template.jinja",
+      "same_inode_as_source": false,
+      "size_bytes": 7764,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/chat_template.jinja"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "config.json",
+      "resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/config.json",
+      "same_inode_as_source": false,
+      "size_bytes": 5541,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/config.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "configuration.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/configuration.json",
+      "same_inode_as_source": false,
+      "size_bytes": 51,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/configuration.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "generation_config.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/generation_config.json",
+      "same_inode_as_source": false,
+      "size_bytes": 202,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/generation_config.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "model-00001-of-00003.safetensors",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model-00001-of-00003.safetensors",
+      "same_inode_as_source": false,
+      "size_bytes": 5343268752,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model-00001-of-00003.safetensors"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "model-00002-of-00003.safetensors",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model-00002-of-00003.safetensors",
+      "same_inode_as_source": false,
+      "size_bytes": 5354185100,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model-00002-of-00003.safetensors"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "model-00003-of-00003.safetensors",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model-00003-of-00003.safetensors",
+      "same_inode_as_source": false,
+      "size_bytes": 5357087747,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model-00003-of-00003.safetensors"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "model.safetensors.index.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/model.safetensors.index.json",
+      "same_inode_as_source": false,
+      "size_bytes": 218281,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/model.safetensors.index.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "mtp.safetensors",
+      "resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3/mtp.safetensors",
+      "same_inode_as_source": false,
+      "size_bytes": 337565787,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/mtp.safetensors"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "mtplx_runtime.json",
+      "resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/mtplx_runtime.json",
+      "same_inode_as_source": false,
+      "size_bytes": 2007,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/mtplx_runtime.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "preprocessor_config.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/preprocessor_config.json",
+      "same_inode_as_source": false,
+      "size_bytes": 390,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/preprocessor_config.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "processor_config.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/processor_config.json",
+      "same_inode_as_source": false,
+      "size_bytes": 1312,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/processor_config.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "tokenizer.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/tokenizer.json",
+      "same_inode_as_source": false,
+      "size_bytes": 19989343,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/tokenizer.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "tokenizer_config.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/tokenizer_config.json",
+      "same_inode_as_source": false,
+      "size_bytes": 1139,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/tokenizer_config.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "video_preprocessor_config.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/video_preprocessor_config.json",
+      "same_inode_as_source": false,
+      "size_bytes": 385,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/video_preprocessor_config.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "vocab.json",
+      "resolved_source_path": "/Users/youssof/.lmstudio/models/mlx-community/Qwen3.6-27B-4bit/vocab.json",
+      "same_inode_as_source": false,
+      "size_bytes": 6722759,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP/vocab.json"
+    },
+    {
+      "materialization": "clonefile",
+      "name": "LICENSE",
+      "resolved_source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v2/LICENSE",
+      "same_inode_as_source": false,
+      "size_bytes": 11343,
+      "source_path": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3/LICENSE"
+    },
+    {
+      "materialization": "generated",
+      "name": "README.md",
+      "resolved_source_path": null,
+      "same_inode_as_source": false,
+      "size_bytes": 3041,
+      "source_path": null
+    },
+    {
+      "materialization": "generated",
+      "name": "NOTICE",
+      "resolved_source_path": null,
+      "same_inode_as_source": false,
+      "size_bytes": 460,
+      "source_path": null
+    }
+  ],
+  "include_hashes": false,
+  "repo_id": "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed",
+  "size_bytes": 16419071404,
+  "source_provenance": {
+    "base_model": "Qwen/Qwen3.6-27B",
+    "base_model_revision": "6a9e13bd6fc8f0983b9b99948120bc37f49c13e9",
+    "license": "Apache-2.0",
+    "mtp_sidecar_revision": "8cc526ddcfdd53346f94fb9b5458ca8495a63218",
+    "mtp_sidecar_source": "cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4"
+  },
+  "source_wrapper": "/Users/youssof/Documents/MTPLX/models/Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP",
+  "staging_dir": "/Users/youssof/Documents/MTPLX/hf-staging/Qwen3.6-27B-MTPLX-Optimized-Speed",
+  "upload_policy": {
+    "recommended_command_after_approval": "HF_HOME=/Users/youssof/.cache/huggingface-mtplx hf upload-large-folder Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed /Users/youssof/Documents/MTPLX/hf-staging/Qwen3.6-27B-MTPLX-Optimized-Speed --private",
+    "requires_explicit_green_light": true,
+    "uploaded": false
+  },
+  "weight_size_bytes": 16392107386
+}

README.md

@@ -0,0 +1,49 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed
+library_name: mlx-lm
+pipeline_tag: text-generation
+tags:
+- mlx
+- mtplx
+- qwen
+- qwen3.6
+- helios
+- union-street-ai
+- local-ai
+- apple-silicon
+- agentic
+---
+
+# Helios Lynx 1.0
+
+Helios Lynx 1.0 is a merged MLX checkpoint from Union Street AI, adapted from `Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed`.
+
+This model is part of the Helios line of local-first agent models. The goal is a practical Apple Silicon model with stronger identity, tool-use judgment, uncertainty calibration, and constitutional behavior for long-running local agents.
+
+It was not trained from scratch by Union Street AI. It is a post-trained adaptation of open model work, packaged here as a merged MLX release for local inference.
+
+## Intended Use
+
+- local AI agents
+- codebase navigation
+- infrastructure reasoning
+- long-context synthesis
+- tool-use planning and recovery
+- Apple Silicon inference experiments
+
+## Notes
+
+This is an experimental release. It is intended for research and local agent work, not high-stakes deployment without independent evaluation.
+
+The release includes the merged MLX weights and MTPLX runtime sidecar files from the base checkpoint so it can be used in MTPLX-aware local runtimes.
+
+## Example
+
+```bash
+python -m mlx_lm generate \
+  --model UnionStreet/Helios-Lynx-1.0 \
+  --prompt "Who are you?"
+```

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}

config.json

@@ -0,0 +1,159 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "image_token_id": 248056,
+    "language_model_only": false,
+    "mlx_lm_extra_tensors": {
+        "mtp_file": "mtp.safetensors",
+        "mtp_tensor_count": 15
+    },
+    "model_type": "qwen3_5",
+    "mtplx_mtp_quantization": {
+        "bits": 4,
+        "description": "Load calibrated CyanKiwi MTP layer linears as packed MLX INT4; keep mtp.fc and MTP norms BF16.",
+        "group_size": 32,
+        "mode": "affine",
+        "policy": "cyankiwi",
+        "prequantized": true
+    },
+    "mtplx_policy": {
+        "base_trunk": "models/Qwen3.6-27B-MLXCommunity-4bit-mtp-graft",
+        "description": "Legacy flat 4-bit MLXCommunity trunk with calibrated CyanKiwi prequantized INT4 MTP sidecar; speed-ceiling probe only, not production default.",
+        "main_policy": "mlx-community-flat-4bit",
+        "mtp_policy": "cyankiwi-calibrated-int4-prequantized",
+        "mtp_sidecar_source": "models/Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3",
+        "name": "mlx-community-4bit-cyankiwi-mtp-speed-probe",
+        "source": "Qwen/Qwen3.6-27B"
+    },
+    "quantization": {
+        "bits": 4,
+        "group_size": 64,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "bits": 4,
+        "group_size": 64,
+        "mode": "affine"
+    },
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "bos_token_id": 248044,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 5120,
+        "initializer_range": 0.02,
+        "intermediate_size": 17408,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 48,
+        "linear_value_head_dim": 128,
+        "mamba_ssm_dtype": "float32",
+        "max_position_embeddings": 262144,
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 24,
+        "num_hidden_layers": 64,
+        "num_key_value_heads": 4,
+        "output_gate_type": "swish",
+        "pad_token_id": null,
+        "partial_rotary_factor": 0.25,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "partial_rotary_factor": 0.25,
+            "rope_theta": 10000000,
+            "type": "default"
+        },
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.1",
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"image-text-to-text"}

generation_config.json

@@ -0,0 +1,12 @@
+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8639a488908985a4f47d0b4bc97ea0435687928b442236b3fe730935fd5071b4
+size 5328325648

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399128514d4763505f533796c1c5d0d34b4f9977f8c568139ed7e256c409498b
+size 5354185130

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cca5d3ddffb0eae027c37f253787a07ba672e3b11a91b47390cc25254388108
+size 4450532735

mtp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc44ee9ddcab9d812b5b1f31399c35c721878a95b7bbf57a318ca28bbb83efb
+size 337565787

mtplx_runtime.json

@@ -0,0 +1,131 @@
+{
+  "arch_id": "qwen3-next-mtp",
+  "artifact_role": "maximum-speed-flat4-candidate",
+  "base_trunk": "mlx-community/Qwen3.6-27B-4bit",
+  "exactness_baseline": {
+    "attention_impl": "mlx_vector_paged",
+    "context": 64,
+    "gate": "phase0h-paged-verifier-exactness",
+    "max_abs_diff": 0.0,
+    "mode": "decode-from-stock-prefix",
+    "sample_agreement": 1.0,
+    "status": "passed",
+    "topk_overlap_ratio": 1.0,
+    "total_variation": 0.0,
+    "verify_tokens": 4
+  },
+  "mtp_depth_max": 3,
+  "mtp_sidecar": "Qwen3.6-27B-MTPLX-CyanKiwi-Packed-BF16-INT4-v3",
+  "mtplx_version": "0.1.0-preview",
+  "recommended_draft_lm_head": {
+    "bits": 3,
+    "group_size": 64,
+    "mode": "affine"
+  },
+  "recommended_draft_sampler": {
+    "temperature": 0.7,
+    "top_k": 20,
+    "top_p": 0.95
+  },
+  "recommended_profile": "performance-cold",
+  "sampler": {
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95
+  },
+  "speed_evidence": {
+    "acceptance_by_depth": [
+      1.0,
+      0.9795918367346939,
+      0.9387755102040817
+    ],
+    "accepted_by_depth": [
+      49,
+      48,
+      46
+    ],
+    "artifacts": [
+      "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_cleanapps_20260503-230229.json",
+      "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_cleanapps_repeat_20260503-230458.json"
+    ],
+    "correction_tokens": 3,
+    "depth": 3,
+    "draft_lm_head": "3-bit affine group64 draft-only head",
+    "draft_sampler": {
+      "temperature": 0.7,
+      "top_k": 20,
+      "top_p": 0.95
+    },
+    "drafted_by_depth": [
+      49,
+      49,
+      49
+    ],
+    "enable_thinking": false,
+    "greedy_diagnostic": {
+      "accepted_by_depth": [
+        49,
+        49,
+        43
+      ],
+      "artifact": "/Users/youssof/.mtplx/fanmax_flat4_full_greedy_cleanapps_20260503-230229.json",
+      "correction_tokens": 0,
+      "draft_sampler": {
+        "temperature": 0.0,
+        "top_k": 0,
+        "top_p": 1.0
+      },
+      "drafted_by_depth": [
+        51,
+        51,
+        51
+      ],
+      "target_sampler": {
+        "temperature": 0.0,
+        "top_k": 0,
+        "top_p": 1.0
+      },
+      "tok_s": 60.108346853627076,
+      "verify_calls": 51
+    },
+    "older_3bit_artifacts": [
+      "/Users/youssof/.mtplx/fanmax_flat4_cyankiwi_draft_head_3bit_isolated_20260503.json",
+      "/Users/youssof/.mtplx/fanmax_flat4_cyankiwi_draft_head_3bit_repeat_20260503.json"
+    ],
+    "older_3bit_tok_s": [
+      60.03822277200243,
+      60.06063543439426
+    ],
+    "previous_best_artifacts": [
+      "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_optimized_env_20260503.json",
+      "/Users/youssof/.mtplx/fanmax_flat4_draft_temp070_repeat_optimized_env_20260503.json"
+    ],
+    "previous_best_tok_s": [
+      61.52744855840259,
+      60.89966247416089
+    ],
+    "production_cli_contract_checks": [
+      {
+        "artifact": "/Users/youssof/.mtplx/fanmax_mtplx_flat4_cyankiwi_cli_contract_perfcold_disablethinking_20260503.json",
+        "tok_s": 59.51602930081416
+      },
+      {
+        "artifact": "/Users/youssof/.mtplx/fanmax_mtplx_flat4_cyankiwi_cli_contract_perfcold_disablethinking_repeat_20260503.json",
+        "tok_s": 59.97165246907193
+      }
+    ],
+    "profile": "performance-cold",
+    "timestamp": "2026-05-03T23:07:00+0100",
+    "tok_s": [
+      63.05651084048216,
+      62.885564723941826
+    ],
+    "verify_calls": 49
+  },
+  "verified_on": {
+    "hardware": "Apple M5 Max, 128 GB unified memory",
+    "machine_arch": "arm64",
+    "model": "Qwen3.6-27B-MTPLX-Flat4-CyanKiwiMTP",
+    "timestamp": "2026-05-03T17:49:00+0100"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,64 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_pixels": 65536,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "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
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "qwen3_coder",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}