Instructions to use rishabhf/bouncer-qwen3.5-4b-mlc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLC-LLM
How to use rishabhf/bouncer-qwen3.5-4b-mlc with MLC-LLM:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
bouncer-qwen3.5-4b-mlc
An unmodified mirror of imbue/Qwen3.5-4B-q4f16_1-MLC-2 (at commit 16b7d99), re-hosted purely for the availability / resilience of the Bouncer browser extension. The weights are byte-for-byte identical to the source — nothing here has been retrained, fine-tuned, or re-quantized.
This repo also carries the matching WebGPU runtime library Qwen3.5-4B-q4f16_1-ctx1k_cs1k-webgpu-2.wasm, mirrored from imbue-ai/binary-mlc-llm-libs at commit 96d72b4, so the weights and their kernels stay pinned together.
Provenance & license
| Base model | Qwen/Qwen3.5-4B — © Qwen Team, Alibaba |
| MLC / WebGPU conversion | imbue/Qwen3.5-4B-q4f16_1-MLC-2 — © Imbue |
| WebGPU kernel library | imbue-ai/binary-mlc-llm-libs |
| License | Apache-2.0 — see LICENSE (carried over from the base model) |
Licensed under the Apache License 2.0. The LICENSE file is the upstream Qwen license. This mirror retains all upstream attribution, makes no modification to the weights, and does not imply endorsement by Qwen, Alibaba, Imbue, or the MLC project.
- Downloads last month
- -