Third-party notices
This repository distributes quantized weights derived from the models below. It contains no third-party code and no runtime artifacts.
| Component | Upstream source and revision | License | Relationship |
|---|---|---|---|
| Base model | Qwen/Qwen3.8-27B, 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0 |
Apache-2.0 | Source of the BF16 linear weights that were quantized. These weights are a quantized derivative. |
| Target checkpoint | unsloth/Qwen3.8-27B-NVFP4, f0b7c9e722f5565102fff8481c99e4d86ae099c7 |
Apache-2.0 | Source of the rotated Gated DeltaNet b/a rows and of the non-linear tensors used during calibration. Required at serving time and not redistributed. |
| DFlash2 draft checkpoint | tcclaviger/Qwen3.8-27B-DFlash2-FP8, ee0cb26a8279b7910cc28d82a8a3e15e4728d56f, derived from z-lab/Qwen3.8-27B-DFlash2 (Apache-2.0) |
Apache-2.0 | Required at serving time, used unchanged and not redistributed. |
| GSQ | IST-DASLab/GSQ, arXiv:2604.18556 | Apache-2.0 | We reimplemented its MSE scale search and use its tensor names. No GSQ code is included. |
| GSQ 3-bit checkpoint | ISTA-DASLab/Qwen3.8-27B-3Bit-GSQ | Apache-2.0 | Source of the calibration category mixture. None of its weights are included. |
| GPTQ | Frantar et al., arXiv:2210.17323 | Method | Quantization algorithm, reimplemented |
| compressed-tensors | vllm-project/compressed-tensors | Apache-2.0 | 3-bit pack_to_int32 storage layout. No code is included. |
| Calibration data | 33 entries, listed in CALIBRATION.md | Apache-2.0, MIT, BSD-3-Clause, ODC-By 1.0, CC BY 4.0 | Used only to collect activation statistics. The data is not redistributed. |
Required attributions for the calibration data
QASC. Tushar Khot, Peter Clark, Michal Guerquin, Peter Jansen and Ashish
Sabharwal, QASC: A Dataset for Question Answering via Sentence Composition,
Allen Institute for AI, allenai/qasc
(revision a34ba204eb9a33b919c10cc08f4f1c8dae5ec070). It is licensed under
CC BY 4.0 and provided as is,
without warranties. We reformatted its facts, questions and answer options into
calibration prompts, and no QASC text is redistributed.
FineWeb-Edu, FineWeb-2 and FinePDFs-Edu. This model's calibration contains information from the following datasets by Hugging Face. They are made available under the ODC Attribution License 1.0, and their use is also subject to Common Crawl's Terms of Use.
- HuggingFaceFW/fineweb-edu, revision
87f09149ef4734204d70ed1d046ddc9ca3f2b8f9 - HuggingFaceFW/fineweb-2, revision
af9c13333eb981300149d5ca60a8e9d659b276b9 - HuggingFaceFW/finepdfs-edu, revision
9cfabe2127faca99b3d5c4dc6d1fcb397399ebde
The Paiton runtime image that loads these weights is distributed separately. Upstream model, method and dataset terms remain those of their sources. The Apache-2.0 license text is in LICENSE.