jianhui42/Qwen3.5-4B-INT4-MixedBlockSize-ONNX-WebGPU
text-generation model by jianhui42
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
ONNX export of the Qwen3.5-4B text decoder for text generation with the WebGPU execution provider. The package contains all 32 decoder layers, tokenizer assets and a chat template. The export uses mixed per-channel and block-wise INT4 weight quantization. The token embedding table uses FP16, and the language-model output head uses INT4. The configured context is 262,144 tokens, and the default total generation limit is 4,096 tokens. The graph exports the text decoder component of Qwen3.5-4B. Its inputs cover token IDs, attention masks, position IDs and decoder cache states. Text generation uses the included tokenizer and chat template. The graph contains 153 MatMulNBits nodes with INT4 weights and accuracylevel=4. Matrices with an input dimension of 4,096 use one scale per output channel. Matrices with input dimensions of 2,560 or 9,216 use 32-element blocks.…
Read the full model card ↗ · Preview checked 2026-11-18T07:52:31.580Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
jianhui42/Qwen3.5-4B-INT4-MixedBlockSize-ONNX-WebGPU is a text-generation model repository published by jianhui42 on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-18T06:20:18.000Z
- Last modified
- 2026-11-18T06:21:22.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.5-4B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-18T07:01:26.893Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.