{
  "artifacts": [
    {
      "file": "Ornith-1.5-9B_int8.litertlm",
      "sha256": "f21058268a2b66a351007a1c3268dba79387943ea27cb595e6203c3b36d05586",
      "size_mb": 8774.598
    }
  ],
  "benchmarks": [],
  "conversion": {
    "command": "convert_qwen35_9b.sh (hf-to-litertlm; ornith-ai/Ornith-1.5-9B at 489cb979, the same script bytes as the Qwen3.5-9B and Ornith-1.0-9B runs): 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 -> the thinking-off template; then the tokenizer step (tools/tokenizer_parity/swap_tokenizer_section.py: the repo's tokenizer.json as the tokenizer section, the other three sections byte-identical)",
    "quantization": "dynamic int8 on every FULLY_CONNECTED + int8 embedding; the convs, the delta rule and the 48 GatedDeltaNet decay/gate projections (in_proj_a / in_proj_b) float; fp32 GPU activations declared (card L31, L107)",
    "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": "2026-10-15",
          "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 (\"$(F $n)\" = Ornith-1.5-9B_int8.litertlm): uvx --from litert-lm==0.17.1 litert-lm run \"$(F $n)\" --backend cpu --prompt \"What is the capital of France? Answer in one word.\" --cache no",
            "bundle: Ornith-1.5-9B_int8.litertlm sha256 f21058268a2b66a351007a1c3268dba79387943ea27cb595e6203c3b36d05586 (now a hard link of Ornith-1.5-9B_int8.litertlm) = the Hugging Face LFS oid of litert-community/Ornith-1.5-9B at main (upload commit 75418dc3), tree API read 2026-10-17 17:48 JST",
            "RAM check: held 3 samples after 120 s (reclaimable 110.2 GB (need 70))",
            "stdout: Paris",
            "EXIT=0",
            "process footprint (swap guard, 15 s samples): max 39 GB; no guard kill",
            "2026-10-15 10:42:18 JST 0.17.1 run int8 exit 0: Paris EXIT=0",
            "Engine.tokenize on the litert-lm 0.17.1 wheel (CPU engine, cache_dir ':nocache', 2026-10-15T11:14:23+0900 .. 2026-10-15T11:15:32+0900): ids equal to the tokenizers library on the repo's tokenizer.json for 174 of 174 probes (21 corpus texts + every gate / eval prompt + the 8 rendered 8-question prompts); detokenize round trip 171 of 174 (the 3 others are NFD inputs that tokenizers itself does not return)"
          ],
          "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,
            "detokenize_roundtrip_equal": 171.0,
            "guard_footprint_max_gb": 39.0,
            "processes": 2.0,
            "tokenize_engine_s": 69.14,
            "tokenize_ids_equal": 174.0,
            "tokenize_probes": 174.0
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/0.17.1/2026-10-15/ornith-1.5-9b-int8__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "cpu",
          "context_length": null,
          "date": "2026-10-15",
          "decode_tokens_per_s": 14.975,
          "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": [
            "command (both passes): litert-lm benchmark Ornith-1.5-9B_int8.litertlm --backend cpu -p 1024 -d 256 --max-num-tokens 2048 --runs 3 --cache no",
            "bundle: Ornith-1.5-9B_int8.litertlm sha256 f21058268a2b66a351007a1c3268dba79387943ea27cb595e6203c3b36d05586 (now a hard link of Ornith-1.5-9B_int8.litertlm) = the Hugging Face LFS oid of litert-community/Ornith-1.5-9B at main (upload commit 75418dc3), tree API read 2026-10-17 17:48 JST",
            "pass 1: prefill 229.74 / decode 14.75 tok/s, TTFT 4.5265 s, init 93.7596 s",
            "pass 2: prefill 238.53 / decode 15.2 tok/s, TTFT 4.359 s, init 89.6482 s",
            "process footprint (swap guard, 15 s samples): max 47 GB as the guard prints it = 50.47 GB in bytes / 1e9 (50.47 / 50.47); no guard kill"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "decode_tokens": 256.0,
            "guard_footprint_max_gb": 47.0,
            "init_s": 91.7039,
            "iterations": 3.0,
            "max_num_tokens": 2048.0,
            "pass1_decode_tok_s": 14.75,
            "pass1_init_s": 93.7596,
            "pass1_prefill_tok_s": 229.74,
            "pass1_ttft_s": 4.5265,
            "pass2_decode_tok_s": 15.2,
            "pass2_init_s": 89.6482,
            "pass2_prefill_tok_s": 238.53,
            "pass2_ttft_s": 4.359,
            "passes": 2.0,
            "prefill_tokens": 1024.0,
            "t_1024_256_s": 21.4741
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": 234.135,
          "provenance": "measured",
          "runs": true,
          "total_ops": null,
          "ttft_ms": 4442.8
        },
        "source": "data/device_runs/0.18.0/2026-10-15/ornith-1.5-9b-int8__mac-studio-m4-max.json"
      },
      {
        "device": "mac-studio-m4-max",
        "run": {
          "accelerator": "gpu",
          "context_length": null,
          "date": "2026-10-15",
          "decode_tokens_per_s": 39.565,
          "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": [
            "command (both passes): litert-lm benchmark Ornith-1.5-9B_int8.litertlm --backend gpu -p 1024 -d 256 --max-num-tokens 2048 --runs 3 --cache no",
            "bundle: Ornith-1.5-9B_int8.litertlm sha256 f21058268a2b66a351007a1c3268dba79387943ea27cb595e6203c3b36d05586 (now a hard link of Ornith-1.5-9B_int8.litertlm) = the Hugging Face LFS oid of litert-community/Ornith-1.5-9B at main (upload commit 75418dc3), tree API read 2026-10-17 17:48 JST",
            "pass 1: prefill 610.19 / decode 40.8 tok/s, TTFT 1.7028 s, init 86.7405 s",
            "pass 2: prefill 607.75 / decode 38.33 tok/s, TTFT 1.7111 s, init 92.7405 s",
            "delegation from the verbose `run` of the same bytes (2026-10-15, the run r5 gate, --backend gpu --cache no --verbose): Replacing 34373 out of 34373 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 0 (prefill_1024). .. Replacing 2920 out of 2920 node(s) with delegate (LITERT_WEBGPU) node, yielding 1 partitions for subgraph 6 (decode). (7 decoder signatures, 132963 / 132963 nodes, one partition each, no 'Validation error' / 'Shape mismatch' line); 2026-10-15 04:33:32 JST gpu run verbose int8 exit 0 replacing=7 validation_error=0 shape_mismatch=0 | reply \"Paris.\"",
            "GPU engine footprint of that verbose run (swap guard): 9.71 GB in bytes / 1e9; the benchmark passes ran without a guard"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": null,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "decode_tokens": 256.0,
            "init_s": 89.7405,
            "iterations": 3.0,
            "max_num_tokens": 2048.0,
            "pass1_decode_tok_s": 40.8,
            "pass1_init_s": 86.7405,
            "pass1_prefill_tok_s": 610.19,
            "pass1_ttft_s": 1.7028,
            "pass2_decode_tok_s": 38.33,
            "pass2_init_s": 92.7405,
            "pass2_prefill_tok_s": 607.75,
            "pass2_ttft_s": 1.7111,
            "passes": 2.0,
            "prefill_tokens": 1024.0,
            "t_1024_256_s": 8.1582
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": 608.97,
          "provenance": "measured",
          "runs": true,
          "total_ops": null,
          "ttft_ms": 1706.9
        },
        "source": "data/device_runs/0.18.0/2026-10-15/ornith-1.5-9b-int8__mac-studio-m4-max.json"
      }
    ]
  },
  "model": {
    "family": "ornith",
    "id": "ornith-1.5-9b-int8",
    "license": "mit",
    "source_url": "https://huggingface.co/litert-community/Ornith-1.5-9B",
    "task": "text-generation"
  },
  "pitfalls": [
    "Text only: the decoder of the multimodal release (8,953,803,264 of its 9,653,104,368 parameters; no vision tower, no MTP head). 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 L25).",
    "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 L21).",
    "Thinking off, no switch: the template writes the empty think block that Ornith's template writes at enable_thinking=False into every assistant turn and the generation prompt; a switch template would drop the think blocks Ornith writes into past turns, so none is shipped (card L27, L77).",
    "One stop token, <|im_end|> (248046): the repo has no generation config and its model config lists that one end token (the Qwen3.5-9B and Ornith-1.0-9B conversions also stop on <|endoftext|>, 248044) (card L77).",
    "Tokenizer: the export writes transformers' Qwen2Tokenizer pipeline (no \\p{M} in the pre-tokenizer) while the repo's tokenizer.json has one; the section was replaced with the repo file, and the runtime's ids equal the tokenizers library's on 174 of 174 probes on litert-lm 0.18.0 and 0.17.1 (card L105).",
    "CPU prompt-length check 15 of 17: at 23 and 24 tokens this file's CPU answered with a polite refusal instead of the asked word, the same in three fresh processes each, while its GPU and the bf16 model kept the word (the bf16 refusal a close second, margins 1.6 / 1.1 logits); the cause is not measured (card L49).",
    "fp32 GPU activations are declared: with the runtime's fp16 default this file answered 0 of 8 check questions (every reply a run of `!`) for 4.5 % less time (card L47, L63).",
    "Tool calling: a tool passed through the API is not rendered (no tool list in the template); with Ornith's own tool block the model writes the call in Qwen3.5's XML form as text, which the runtime does not parse or run (LiteRT-LM issue 3927); a tool result sent back as a `tool` message was not used (card L79).",
    "One Engine per conversation: the runtime starts a new Conversation from the earlier one's recurrent state (LiteRT-LM issue 3165); the probe on these files gave the same answers on a shared and a fresh Engine, but the state is carried all the same (card L81).",
    "Galaxy S26: the int8 file was not started on the phone's GPU (a sibling 8B-class int8 file restarted the phone during its GPU warm-up) and the CPU was not run (13.8 GB by the earlier CPU peak factor against 11.66 GB); Pixel 8a not run; not run on an NPU (card L98-L100).",
    "iOS not measured: one 8.57 GiB TFLite section, over the ~2 GiB single-section limit (card L43).",
    "Accuracy: GSM8K n=100 (thinking off, greedy, at most 2,048 output tokens, Mac GPU): bf16 94 / int8 95, agreeing on 93 of 100 questions (card L57-L63).",
    "Mac: the faster file on the CPU (21.47 vs 32.37 s; prefill 234 vs 68 tok/s) and the slower on the GPU (8.16 vs 7.28 s); without --cache, the first CPU `run` writes a 7.99 GB compiled-weights cache next to the model; the CLI's printed init sums overlapping init phases (card L38-L43, L75, L85)."
  ],
  "schema_version": "1.2"
}
