Qwen3-1.7B (q4f16_1, WebLLM)

models.skillsafe.ai/qwen3-1.7b-q4f16@80b3abcec6c3/

Vetted New WebGPU

Text generation model for web-llm (q4f16_1). Runs on WebGPU — 929 MB downloaded once from models.skillsafe.ai, then cached for every SkillSafe app that uses it. Inference happens on your device; nothing you enter is uploaded to load it, and it never costs a credit. Weights from Hugging Face · skillsafe-ai/qwen3-1.7b-q4f16, pinned at 71023361689c — also loadable straight from Hugging Face outside SkillSafe (how).

text generation web-llm WebGPU q4f16_1 Apache-2.0
Use it in an app Browse all models Request a variant
Share

Details

Catalogue idqwen3-1.7b-q4f16@80b3abcec6c3
Tasktext generation
Runtimeweb-llm ≥ 0.2.80
DeviceWebGPU
Variantq4f16_1
Download929 MB · 31 files
LicenceApache-2.0 · notice
SourceHugging Face · skillsafe-ai/qwen3-1.7b-q4f16
Pinned at71023361689cc1f72d68985478dffb5be62eeb8b
ApprovedSep 22, 2026
Statusactive — every file is a live vetted hash
API/v1/browser-models/qwen3-1.7b-q4f16

Files

Each file is served at an immutable URL; the canonical form is the SHA-256 itself. Tokenizer and config JSON are not here by design — they ship in your app bundle.

PathFormatSizeSHA-256
params_shard_0.bin bin 148 MB a7abd640b7fd…dd0394
params_shard_1.bin bin 25.3 MB 2f14002a930e…c2fef1
params_shard_10.bin bin 27.0 MB bd23d892a34d…610025
params_shard_11.bin bin 27.0 MB 375fd71377c3…9ab48e
params_shard_12.bin bin 27.0 MB ddb3a9bca9c4…8d0221
params_shard_13.bin bin 27.0 MB 4e3b4a295253…a77dea
params_shard_14.bin bin 27.0 MB f42d833546e9…044697
params_shard_15.bin bin 27.0 MB 2f2212c72b6c…4d0619
params_shard_16.bin bin 27.0 MB a4ac8a50804c…6965c5
params_shard_17.bin bin 27.0 MB 073fbe52bb87…8498cc
params_shard_18.bin bin 27.0 MB 189c984a8b40…5d9c9a
params_shard_19.bin bin 27.0 MB 62c38dbbaf33…ac3286
params_shard_2.bin bin 27.0 MB 3654b87f3996…e77758
params_shard_20.bin bin 27.0 MB 00c9d9217df1…1fb036
params_shard_21.bin bin 27.0 MB e0d11a218bfd…bf4c99
params_shard_22.bin bin 27.0 MB 3052929ab7e9…1e37e4
params_shard_23.bin bin 27.0 MB 081d7ca07571…c348ec
params_shard_24.bin bin 27.0 MB 29c885aa1611…836aa6
params_shard_25.bin bin 27.0 MB 3d4ef25ac005…bf95ed
params_shard_26.bin bin 27.0 MB c445d07299ae…a81bcb
params_shard_27.bin bin 27.0 MB 36568084cf5f…a9d72c
params_shard_28.bin bin 27.0 MB 498df665b674…59cd26
params_shard_29.bin bin 20.3 MB 9170848cd44c…dad7ac
params_shard_3.bin bin 27.0 MB 2efefd0faded…149175
params_shard_4.bin bin 27.0 MB e10d4e1f3577…9ad3de
params_shard_5.bin bin 27.0 MB 6cdb44dfa357…70c2b1
params_shard_6.bin bin 27.0 MB a03ee4f5ffb3…edad40
params_shard_7.bin bin 27.0 MB 510a44ed7477…eab027
params_shard_8.bin bin 27.0 MB 596cdddab0c8…123ac9
params_shard_9.bin bin 27.0 MB 83291442b024…158e7e
lib/Qwen3-1.7B-q4f16_1-ctx4k_cs1k-webgpu.wasm wasm 5.5 MB 8b0acc85b34e…3d3b06
Use it in an app declaration · SDK loader · web-llm · URLs · Hugging Face — generated from this entry

Add to the body of POST /v1/apps/{slug}/releases (or a release session). An unknown or withdrawn model is refused with a 400 naming it; the app page then shows "downloads 929 MB · runs on your device" and /models.txt carries the attribution.

{
  "models": [
    {
      "id": "qwen3-1.7b-q4f16",
      "revision": "80b3abcec6c3"
    }
  ]
}

Evaluation

shard sizes + md5 vs ndarray-cache.json; implied parameter count vs the checkpoint; parameter table vs model_lib embedded metadata — MLC's published weights, checked against the WebGPU library. Evaluated Sep 22, 2026.

Library fit

params_matched: 339 · symbolic_dims_resolved: [] · model_type: qwen3 · quantization: q4f16_1 · effective: {"context_window_size":4096,"prefill_chunk_size":1024}

Toolchain: python 3.12.13 · platform Darwin 25.6.0 arm64 · torch 2.10.0 · onnx 1.23.0 · onnxruntime 1.30.0. Recipe models/recipes/qwen3-1.7b-q4f16.yaml (f5e2c15375c1). Full manifest.json

Licence & attribution

Apache-2.0 · licence text · notice

Qwen3-1.7B: Copyright 2025 Alibaba Cloud. Apache License 2.0. https://huggingface.co/Qwen/Qwen3-1.7B — q4f16_1 weights published by MLC (https://huggingface.co/mlc-ai/Qwen3-1.7B-q4f16_1-MLC).

Apps that declare this model get this text in their generated /models.txt, so a licence that requires a notice always carries one.

Revisions

RevisionVariantSizeApprovedStatusApps
qwen3-1.7b-q4f16@80b3abcec6c3 q4f16_1 929 MB Sep 22, 2026 active 0
qwen3-1.7b-q4f16@80b3abce q4f16_1 923 MB Sep 22, 2026 withdrawn 0

Every file here was approved by exact SHA-256 after a structural audit of the graph, fetched from a content-pinned source, and is served credential-free at an immutable URL. The SDK re-verifies the hash on your device before it caches or returns anything. Missing a variant? Request it — or read how the registry works.