{
  "artifacts": [
    {
      "file": "Qwen3.5-9B_mixed_int4.litertlm",
      "sha256": "61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65",
      "size_mb": 5779.607
    }
  ],
  "benchmarks": [],
  "conversion": {
    "command": "convert_qwen35_9b.sh (hf-to-litertlm; Qwen/Qwen3.5-9B at c2022362): text-decoder export (6 prefill signatures 1024..1 + decode, a 4096-position KV budget, 64 state buffers) -> int8 / Mixed INT4 quantization with the 48 in_proj_a / in_proj_b projections float -> fp32 GPU activations declared; then the tokenizer step (the repo's tokenizer.json as the tokenizer section) and use_switch_template.sh (the Qwen3.5-4B files' template, thinking switch and thought channel)",
    "quantization": "Mixed INT4: int4 blockwise-32 min-max on the linear layers, int8 on the lm_head and the embedding, the 48 decay/gate projections float; 216,006,656 block scales, all normal floats (none zero or subnormal); fp32 GPU activations declared (card L31, L108)",
    "tool": "litert-torch (pinned commit 115a1360 + the Qwen3.5 hybrid patch of hf-to-litertlm, 2026-08-21 version; lightweight export with a 1e8-byte lazy-constant threshold) + post-hoc ai-edge-quantizer; repro = hf-to-litertlm qwen35_work/",
    "tool_version": "litert-torch 115a1360 + patch, transformers 5.14.1, torch 2.12.1, ai-edge-quantizer 0.8.0; packed and checked with litert-lm 0.18.0"
  },
  "cross_runtime": [],
  "delegation": null,
  "device": {
    "records": [
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "cpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.18.0",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "harness: 8 fixed questions (scripts/verify_quality.py's checks) each with an ' Answer briefly.' suffix, one `litert-lm run <file> --prompt <question> --backend cpu --cache disk --temperature 0 --seed 0` process per question (litert-lm 0.18.0 CLI), judged by a regex per question and a degeneracy rule (a reply of repeated words or an empty reply)",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST; read through the XNNPACK cache dir's hard link Qwen3.5-9B_mixed_int4.litertlm",
            "score 8/8 (pass mark 6), degenerate 0; rhyme item answer \"blue.\"",
            "2026-10-16 14:30:58 JST cpu step q8 done"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "gate_pass_mark": 6.0,
            "gate_rows_passed": 8.0,
            "gate_rows_run": 8.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "8-question check (CLI run --cache disk)",
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.18.0/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "cpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.17.1",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "command (tools/t1/slotpass.sh, \"$(F $n)\"): uvx --from litert-lm==0.17.1 litert-lm run \"$(F $n)\" --backend cpu --prompt \"What is the capital of France? Answer in one word.\" --cache no",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST",
            "RAM check: held 3 samples after 120 s (reclaimable 103.3 GB (need 70))",
            "stdout: Paris",
            "EXIT=0"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "answers_with_expect": 1.0,
            "processes": 1.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "one prompt (CLI run --cache no)",
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.17.1/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "cpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.18.0",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "harness: gate_multiturn_t1.py on the litert-lm 0.18.0 wheel's Engine / Conversation API, one process = one Engine = one Conversation, SamplerConfig(top_k=1, seed=0), max_num_tokens 4096, CPU, XNNPACK cache dir; no ThinkingConfig (the template's default = thinking off), 256 output tokens per turn: \"Give me one word that means 'very big'.\" / \"Use it in a short sentence.\" / \"Now make that sentence a question.\"; PASS = every reply non-empty with no chat marker and the token count growing",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST; read as",
            "turn 1: reply \"Colossal\", token_count -> 25, thought 0 characters",
            "turn 2: reply \"The colossal mountain towered above the valley.\", token_count -> 54, thought 0 characters",
            "turn 3: reply \"How could such a colossal mountain tower above the valley?\", token_count -> 85, thought 0 characters"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "engine_s": 22.9,
            "max_num_tokens": 4096.0,
            "max_output_tokens": 256.0,
            "turn1_elapsed_s": 2.6,
            "turn1_kv_before_decode": 22.0,
            "turn1_render_tokens": 22.0,
            "turn1_thought_chars": 0.0,
            "turn1_token_count": 25.0,
            "turn2_elapsed_s": 1.3,
            "turn2_kv_before_decode": 44.0,
            "turn2_render_tokens": 41.0,
            "turn2_thought_chars": 0.0,
            "turn2_token_count": 54.0,
            "turn3_elapsed_s": 1.5,
            "turn3_kv_before_decode": 73.0,
            "turn3_render_tokens": 67.0,
            "turn3_thought_chars": 0.0,
            "turn3_token_count": 85.0,
            "turns_passed": 3.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "three-turn conversation, thinking off (Python API)",
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.18.0/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "cpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.18.0",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "harness: gate_multiturn_t1.py on the litert-lm 0.18.0 wheel's Engine / Conversation API, one process = one Engine = one Conversation, SamplerConfig(top_k=1, seed=0), max_num_tokens 4096, CPU, XNNPACK cache dir; ThinkingConfig(enable_thinking=True, thinking_token_budget=300), 2,048 output tokens per turn: \"My name is Kenji.\" / \"What is 17 times 23?\" / \"What is my name?\"; PASS = a closed thought every turn, 391 in reply 2, Kenji in reply 3, and the KV before each decode growing and equal to the token count of the bundle template's render (the runtime takes each thought out of the KV before the next turn)",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST; read as",
            "turn 1: reply \"Hello Kenji! It's nice to meet you. How can I assist you today?\", token_count -> 338, thought 1073 characters",
            "turn 2: reply \"17 times 23 is **391**.\n\nHere is the breakdown:\n$$17 \\times 23 = 391$$\", token_count -> 391, thought 687 characters",
            "turn 3: reply \"Your name is Kenji.\", token_count -> 412, thought 1034 characters"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "engine_s": 23.3,
            "max_num_tokens": 4096.0,
            "max_output_tokens": 2048.0,
            "turn1_elapsed_s": 27.1,
            "turn1_kv_before_decode": 16.0,
            "turn1_render_tokens": 16.0,
            "turn1_thought_chars": 1073.0,
            "turn1_token_count": 338.0,
            "turn2_elapsed_s": 24.9,
            "turn2_kv_before_decode": 54.0,
            "turn2_render_tokens": 54.0,
            "turn2_thought_chars": 687.0,
            "turn2_token_count": 391.0,
            "turn3_elapsed_s": 22.9,
            "turn3_kv_before_decode": 102.0,
            "turn3_render_tokens": 102.0,
            "turn3_thought_chars": 1034.0,
            "turn3_token_count": 412.0,
            "turns_passed": 3.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "three-turn conversation, thinking on with thinking_token_budget 300 (Python API)",
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.18.0/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "gpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": 34373,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.18.0",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "harness: 8 fixed questions (scripts/verify_quality.py's checks) each with an ' Answer briefly.' suffix, one `litert-lm run <file> --prompt <question> --backend gpu --cache no --temperature 0 --seed 0` process per question (litert-lm 0.18.0 CLI), judged by a regex per question and a degeneracy rule (a reply of repeated words or an empty reply)",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST; read as",
            "score 8/8 (pass mark 6), degenerate 0; rhyme item answer \"blue.\"",
            "2026-10-16 12:16:55 JST gpu step q8 done",
            "delegation: a separate verbose run of the same file, \"$CLI\" run \"$p\" --backend gpu --prompt \"What is the capital of France? Answer briefly.\" --cache no --temperature 0 --seed 0 --verbose (tools/t1/gate_t1.sh step verbose): 7 of 7 decoder signatures replaced whole on LITERT_WEBGPU, one partition each, no 'Validation error' / 'Shape mismatch' line, reply \"The capital of France is Paris.\"",
            "VERBOSE: Replacing 34373 out of 34373 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 0 (prefill_1024).",
            "VERBOSE: Replacing 25157 out of 25157 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 1 (prefill_256).",
            "VERBOSE: Replacing 22469 out of 22469 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 2 (prefill_64).",
            "VERBOSE: Replacing 22589 out of 22589 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 3 (prefill_16).",
            "VERBOSE: Replacing 22589 out of 22589 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 4 (prefill_4).",
            "VERBOSE: Replacing 2866 out of 2866 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 5 (prefill_1).",
            "VERBOSE: Replacing 2920 out of 2920 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 6 (decode)."
          ],
          "failure_class": null,
          "full_delegation": true,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "gate_pass_mark": 6.0,
            "gate_rows_passed": 8.0,
            "gate_rows_run": 8.0,
            "verbose_signatures_replaced_whole": 7.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "8-question check (CLI run --backend gpu --cache no)",
          "total_ops": 34373,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.18.0/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "gpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.18.0",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "harness: gate_multiturn_t1.py on the litert-lm 0.18.0 wheel's Engine / Conversation API, one process = one Engine = one Conversation, SamplerConfig(top_k=1, seed=0), max_num_tokens 4096, GPU, XNNPACK cache dir ../../../litert-compat/:nocache; no ThinkingConfig (the template's default = thinking off), 256 output tokens per turn: \"Give me one word that means 'very big'.\" / \"Use it in a short sentence.\" / \"Now make that sentence a question.\"; PASS = every reply non-empty with no chat marker and the token count growing",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST; read as",
            "turn 1: reply \"Colossal\", token_count -> 25, thought 0 characters",
            "turn 2: reply \"The colossal mountain towered above the clouds.\", token_count -> 54, thought 0 characters",
            "turn 3: reply \"How could anyone climb the colossal mountain?\", token_count -> 82, thought 0 characters"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "engine_s": 50.9,
            "max_num_tokens": 4096.0,
            "max_output_tokens": 256.0,
            "turn1_elapsed_s": 0.5,
            "turn1_kv_before_decode": 22.0,
            "turn1_render_tokens": 22.0,
            "turn1_thought_chars": 0.0,
            "turn1_token_count": 25.0,
            "turn2_elapsed_s": 0.6,
            "turn2_kv_before_decode": 44.0,
            "turn2_render_tokens": 41.0,
            "turn2_thought_chars": 0.0,
            "turn2_token_count": 54.0,
            "turn3_elapsed_s": 0.6,
            "turn3_kv_before_decode": 73.0,
            "turn3_render_tokens": 67.0,
            "turn3_thought_chars": 0.0,
            "turn3_token_count": 82.0,
            "turns_passed": 3.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "three-turn conversation, thinking off (Python API)",
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.18.0/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "gpu",
          "context_length": null,
          "date": "2026-10-16",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Mac Studio (M4 Max, Mac16,9)",
            "machine_label": "mac-studio-m4-max",
            "os_build": "macOS 27.0 (26A428)",
            "runtime": "litert-lm",
            "runtime_version": "0.18.0",
            "soc": "Apple M4 Max",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "harness: gate_multiturn_t1.py on the litert-lm 0.18.0 wheel's Engine / Conversation API, one process = one Engine = one Conversation, SamplerConfig(top_k=1, seed=0), max_num_tokens 4096, GPU, XNNPACK cache dir ../../../litert-compat/:nocache; ThinkingConfig(enable_thinking=True, thinking_token_budget=300), 2,048 output tokens per turn: \"My name is Kenji.\" / \"What is 17 times 23?\" / \"What is my name?\"; PASS = a closed thought every turn, 391 in reply 2, Kenji in reply 3, and the KV before each decode growing and equal to the token count of the bundle template's render (the runtime takes each thought out of the KV before the next turn)",
            "bundle: Qwen3.5-9B_mixed_int4.litertlm sha256 61042ebd3c473763972d22310c055f63fab5a29bc2976ab533d6a59c262cac65 = the Hugging Face LFS oid of litert-community/Qwen3.5-9B at main (upload commit 06047197), tree API read 2026-10-17 17:15 JST; read as Qwen3.5-9B_mixed_int4.litertlm",
            "turn 1: reply \"Hello Kenji! It's nice to meet you. How can I assist you today?\", token_count -> 338, thought 1062 characters",
            "turn 2: reply \"17 times 23 is **391**.\n\nHere is the breakdown:\n$$17 \\times 23 = 391$$\", token_count -> 391, thought 931 characters",
            "turn 3: reply \"Your name is **Kenji**.\", token_count -> 413, thought 1012 characters"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "engine_s": 53.9,
            "max_num_tokens": 4096.0,
            "max_output_tokens": 2048.0,
            "turn1_elapsed_s": 7.7,
            "turn1_kv_before_decode": 16.0,
            "turn1_render_tokens": 16.0,
            "turn1_thought_chars": 1062.0,
            "turn1_token_count": 338.0,
            "turn2_elapsed_s": 10.2,
            "turn2_kv_before_decode": 54.0,
            "turn2_render_tokens": 54.0,
            "turn2_thought_chars": 931.0,
            "turn2_token_count": 391.0,
            "turn3_elapsed_s": 8.5,
            "turn3_kv_before_decode": 102.0,
            "turn3_render_tokens": 102.0,
            "turn3_thought_chars": 1012.0,
            "turn3_token_count": 413.0,
            "turns_passed": 3.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "signature": "three-turn conversation, thinking on with thinking_token_budget 300 (Python API)",
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.18.0/2026-10-16/qwen35-9b-mixed-int4__mac-studio-m4-max.json"
      }
    ]
  },
  "model": {
    "family": "qwen3.5",
    "id": "qwen35-9b-mixed-int4",
    "license": "apache-2.0",
    "source_url": "https://huggingface.co/litert-community/Qwen3.5-9B",
    "task": "text-generation"
  },
  "pitfalls": [
    "Text only: the decoder of the multimodal release; no image or video input. Only the 8 attention layers keep a growing KV cache (a 4096-token budget); the 24 linear-attention layers carry a constant-size conv and recurrent state (card L24).",
    "Runtime: tested on litert-lm 0.18.0 (Mac); on litert-lm 0.17.1 the file answered a plain `run` with \"Paris\" (Mac CPU, one run) (card L20).",
    "Thinking is off unless asked (the Qwen3.5-4B files' template, a `thought` channel). With thinking on and no budget a 12-pencil word problem kept this file's thought open to the 2,048-token cap in 3 of 3 CPU runs and a three-turn conversation left turns empty at 1,024 tokens per turn on both backends; with thinking_token_budget 300 every measured thought closed (card L52, L77).",
    "Galaxy S26 GPU: the engine of this file does not build on a phone of this memory class: on a device-lab Galaxy S26 the session ended during the engine build after the delegate had taken two prefill signatures, with the low-memory killer removing other apps, and the same-architecture Ornith-1.0-9B files failed four sessions the same way, a three-signature variant included; the CPU was not run (12.1 GB by earlier CPU peak factors against 11.66 GB) (card L96, L100).",
    "fp32 GPU activations are declared (the int8 sibling answered 0 of 8 with the runtime's fp16 default) (card L46, L96).",
    "One Engine per conversation: on a shared Engine the second conversation broke in 1 of 3 runs of this file (every reply a repeated `</think>`); LiteRT-LM issue 3165 (card L83).",
    "Conversation preface with tools and no messages: LiteRT-LM renders the chat template with an empty message list, and the template reads messages[0] without checking that the list is non-empty, so the render fails with 'Failed to apply template: undefined value' when the preface is prefilled at creation (prefillPrefaceOnInit, default false; creating the conversation fails) and in the preface render (renderPrefaceIntoString and its C++ and C API forms); the same with extra context (such as enable_thinking) and no messages, and in the preface render with an empty preface (run in the runtime on one Qwen3 template; the other templates rendered with minijinja 2.14 and jinja2); read in the source of LiteRT-LM 0.17.0, 0.18.1 and main, measured with the 0.18.1 PyPI package through its C API on these files' template text; the default path, where the first message is rendered with the preface, is not affected (the 0.18.1 Python API and CLI expose neither the flag nor the preface render); a system message or any initial message in the conversation config avoids it (card L113).",
    "Tool calling: the model writes the call in Qwen3.5's XML form as text; the runtime does not parse or run it (LiteRT-LM issue 3927) (card L81).",
    "Tokenizer: the tokenizer section is the repo's tokenizer.json byte for byte (346 of 346 strings match the tokenizers library) (card L79).",
    "Init: the 0.18.0 CLI's printed init sums overlapping init phases (LiteRT-LM #4057) — this file's GPU run printed 89.2 s for a 44.5 s engine build; each of the 7 signature graphs compiles on one thread (card L87).",
    "Pixel 8a: not run (no Qwen3.5 Hub file built a GPU engine on this Mali phone under a memory guard) (card L101). iOS not measured: one 5.64 GiB TFLite section, over the ~2 GiB single-section limit (card L42).",
    "Accuracy: GSM8K n=100 (thinking off, greedy, at most 2,048 output tokens, Mac GPU): bf16 97 / Mixed INT4 95; three of its replies (questions 38, 41, 62) reached the 2,048-token cap without a final line and count as wrong; the file is 34 % smaller than the int8 file (card L33, L58-L64).",
    "Mac: the Mixed INT4 file is the faster file on the GPU (13.9 % less time, decode 46.1 vs 38.4 tok/s) and the slower on the CPU (blockwise prefill 66 tok/s against 228); without --cache, `run` writes a 4.96 GB compiled-weights cache next to the model; the benchmark and GSM8K ran on files whose TFLite section is byte-identical to this file's (card L42, L64, L77)."
  ],
  "schema_version": "1.2"
}
