Kingy and native LM Studio: three paired PDF repetitions

• A1: runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.
• A2: runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.
• A3: runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.
• B1: Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export.
• B2: Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export.
• B3: Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export.

{
  "workflowVersion": "1.5.1",
  "runnerSha256": "abc2334bfb7b4727eee31f61f11da50512ac30ee2585d9974232ae2231276ef8",
  "configuration": {
    "machine": {
      "platform": "apple-silicon",
      "chip": "M4 Pro",
      "model": "Mac16,7",
      "cpuCores": 14,
      "gpuCores": 20,
      "memoryGiB": 24,
      "osFamily": "macOS",
      "osVersion": "26.3",
      "osBuild": "25D125"
    },
    "runtime": {
      "name": "llama.cpp",
      "version": "b11429",
      "commit": "d81235049",
      "binarySha256": "51afbf4ea6485b9ada19e99af97181f12baca42ef704b1e291c26a9ac0644eae"
    },
    "python": "3.12.14",
    "pypdf": "6.10.0",
    "model": {
      "id": "Qwen3-4B",
      "quantization": "Q4_K_M",
      "repository": "Qwen/Qwen3-4B-GGUF",
      "revision": "bc640142c66e1fdd12af0bd68f40445458f3869b",
      "file": "Qwen3-4B-Q4_K_M.gguf",
      "bytes": 2497280256,
      "sha256": "7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5",
      "license": "Apache-2.0"
    }
  },
  "generationSeed": 271828,
  "context": 8192,
  "temperature": 0,
  "maxOutputTokens": 512,
  "thinking": false,
  "cpuThreads": 10,
  "gpuOffload": "full Metal",
  "parallel": 1,
  "flashAttention": true,
  "kv": "F16",
  "retrieval": "Local BM25 pages and field/clause selection, source-ID selection, then local sufficiency inference",
  "answerModelRequests": [
    77,
    77,
    77
  ],
  "warmupRequests": 3,
  "cachePolicy": "cache_prompt false; no claim that OS file caches were flushed.",
  "timingBoundary": "runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.",
  "nativeEgressComparison": "unverified; no comparative privacy claim"
}

Actual Kingy settings and complete-answer timing boundary

{
  "load_config": {
    "fields": [
      {
        "key": "llm.load.llama.autoFit",
        "value": false
      },
      {
        "key": "llm.load.mlx.autoFit",
        "value": false
      },
      {
        "key": "llm.load.llama.cpuThreadPoolSize",
        "value": 10
      },
      {
        "key": "llm.load.contextLength",
        "value": 8192
      },
      {
        "key": "llm.load.llama.flashAttention",
        "value": true
      },
      {
        "key": "llm.load.promptTemplate",
        "value": {
          "type": "jinja",
          "jinjaPromptTemplate": {
            "template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for index in range(ns.last_query_index, -1, -1) %}\n    {%- set message = messages[index] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not('<tool_response>' in message.content and '</tool_response>' in message.content) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}"
          }
        }
      },
      {
        "key": "llm.load.llama.tryDirectIO",
        "value": false
      },
      {
        "key": "llm.load.llama.acceleration.offloadRatio",
        "value": 1
      },
      {
        "key": "llm.load.numParallelSessions",
        "value": 1
      },
      {
        "key": "llm.load.seed",
        "value": {
          "checked": true,
          "value": 271828
        }
      },
      {
        "key": "llm.load.yuzu.autoFit",
        "value": false
      },
      {
        "key": "llm.load.vllm.autoFit",
        "value": false
      }
    ]
  },
  "prediction_config": {
    "fields": [
      {
        "key": "llm.prediction.promptTemplate",
        "value": {
          "type": "jinja",
          "jinjaPromptTemplate": {
            "template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for index in range(ns.last_query_index, -1, -1) %}\n    {%- set message = messages[index] %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not('<tool_response>' in message.content and '</tool_response>' in message.content) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}"
          },
          "stopStrings": []
        }
      },
      {
        "key": "llm.prediction.llama.cpuThreads",
        "value": 10
      },
      {
        "key": "llm.prediction.repeatPenalty",
        "value": {
          "checked": true,
          "value": 1
        }
      },
      {
        "key": "llm.prediction.topPSampling",
        "value": {
          "checked": true,
          "value": 1
        }
      },
      {
        "key": "llm.prediction.minPSampling",
        "value": {
          "checked": true,
          "value": 0
        }
      },
      {
        "key": "llm.prediction.temperature",
        "value": 0
      },
      {
        "key": "llm.prediction.maxPredictedTokens",
        "value": {
          "checked": true,
          "value": 512
        }
      },
      {
        "key": "llm.prediction.reasoning.enableThinking",
        "value": false
      },
      {
        "key": "llm.prediction.contextOverflowPolicy",
        "value": "stopAtLimit"
      },
      {
        "key": "llm.prediction.tools",
        "value": {
          "type": "none"
        }
      }
    ]
  },
  "plugins": [
    "lmstudio/rag-v1"
  ],
  "plugin_configs": {
    "lmstudio/rag-v1": {
      "preset": "",
      "config": {
        "fields": [
          {
            "key": "retrievalLimit",
            "value": 8
          }
        ]
      }
    }
  },
  "system_prompt": ""
}

Frozen effective native settings checked on every measured answer