{
  "claim": "A per-option System One scorer in the browser costs a WASM runtime before it costs any weights, and that runtime is larger uncompressed than the smallest model in the ladder. Loading the default model in the widget on this page transferred 90.45 MiB across 18 requests, measured in the real page rather than read off a model card.",
  "method": "Two columns. 'uncompressed' is the response body size served without content-encoding, recorded through a local recording proxy in headless Chromium 141 (transformers.js 4.3.0, ONNX Runtime Web 1.31.0-dev). 'transferred' is what the same file actually cost over the wire when the widget on this page loaded it from huggingface.co and cdn.jsdelivr.net, which compress. Every figure is MiB = 1,048,576 bytes.",
  "source": "https://huggingface.co/Xenova/nli-deberta-v3-xsmall, https://huggingface.co/Xenova/mobilebert-uncased-mnli, https://huggingface.co/onnx-community/ModernBERT-large-zeroshot-v2.0-ONNX, https://huggingface.co/heman10x/rlcd-modernbert-151m",
  "captured": "2026-09-19",
  "note": "The .onnx weights barely compress \u2014 they are already-quantised tensor data \u2014 while the WASM runtime and the tokenizer JSON compress by 4-5x. That is why the runtime looks frightening uncompressed and is tolerable in practice, and why the weights are the number that decides whether you ship this. The two rlcd-modernbert-151m rows are exact byte counts from the Hub for the only open System One model with a browser playground; it publishes no int8 or 4-bit export at all.",
  "columns": [
    {
      "key": "what",
      "label": "fetched",
      "align": "left"
    },
    {
      "key": "kind",
      "label": "kind",
      "align": "left"
    },
    {
      "key": "raw",
      "label": "uncompressed MiB",
      "align": "right",
      "mono": true
    },
    {
      "key": "wire",
      "label": "transferred MiB",
      "align": "right",
      "mono": true
    }
  ],
  "rows": [
    {
      "what": "ort-wasm-simd-threaded.asyncify.wasm (jsDelivr)",
      "kind": "runtime",
      "raw": 25.62,
      "wire": 5.29
    },
    {
      "what": "transformers.js bundle",
      "kind": "runtime",
      "raw": 1.28,
      "wire": "app chunk"
    },
    {
      "what": "nli-deberta-v3-xsmall \u2014 model_quantized.onnx (q8)",
      "kind": "weights 70M",
      "raw": 83.2,
      "wire": 83.2
    },
    {
      "what": "nli-deberta-v3-xsmall \u2014 tokenizer.json",
      "kind": "weights 70M",
      "raw": 8.26,
      "wire": 1.94
    },
    {
      "what": "mobilebert-uncased-mnli \u2014 model_quantized.onnx (q8)",
      "kind": "weights 25M",
      "raw": 25.72,
      "wire": "\u2014"
    },
    {
      "what": "mobilebert-uncased-mnli \u2014 tokenizer.json",
      "kind": "weights 25M",
      "raw": 0.68,
      "wire": "\u2014"
    },
    {
      "what": "ModernBERT-large-zeroshot-v2.0 \u2014 model_q4f16.onnx",
      "kind": "weights 395M",
      "raw": 283.61,
      "wire": "\u2014"
    },
    {
      "what": "ModernBERT-large-zeroshot-v2.0 \u2014 tokenizer.json",
      "kind": "weights 395M",
      "raw": 3.42,
      "wire": "\u2014"
    },
    {
      "what": "rlcd-modernbert-151m \u2014 model_fp16.onnx (303,785,047 B)",
      "kind": "weights 151M",
      "raw": 289.71,
      "wire": "\u2014"
    },
    {
      "what": "rlcd-modernbert-151m \u2014 model.onnx (606,323,181 B)",
      "kind": "weights 151M",
      "raw": 578.24,
      "wire": "\u2014"
    },
    {
      "what": "TOTAL for one click on the default model, in the real page",
      "kind": "18 requests",
      "raw": "\u2014",
      "wire": 90.45
    }
  ]
}