K2-Horizon-7B-MXFP8 is an open-weight model from Use-AI, released under Apache License 2.0. Its published files total 2.8 KB.
MXFP8-quantized version of IFM/K2-Horizon-7B, targeting NVIDIA Blackwell GPUs. This repository provides an MXFP8 conversion of K2-Horizon-7B for use with block-scaled FP8 inference runtimes.
Model Card
By Use-AI, published under apache-2.0, revision 13cbef75ec9a.
MXFP8-quantized version of IFM/K2-Horizon-7B, targeting NVIDIA Blackwell GPUs. This repository provides an MXFP8 conversion of K2-Horizon-7B for use with block-scaled FP8 inference runtimes. The model weights were converted to MXFP8 using: - Blackwell-compatible block-scaled matrix multiplication The converted model contains approximately 254 MXFP8 modules. IFM/K2-Horizon-7B Please refer to the original model card for architecture details, training information, intended use, and limitations. The main quantized checkpoint is provided in SafeTensors format. Users should also obtain or use the corresponding configuration, tokenizer, and model architecture files from the original K2-Horizon-7B…
Read Use-AI's full model card
MXFP8-quantized version of IFM/K2-Horizon-7B, targeting NVIDIA Blackwell GPUs.
This repository provides an MXFP8 conversion of K2-Horizon-7B for use with block-scaled FP8 inference runtimes.
Quantization
The model weights were converted to MXFP8 using:
- E4M3 FP8 values
- E8M0 block scaling
- Blackwell-compatible block-scaled matrix multiplication
- SafeTensors checkpoint format
The converted model contains approximately 254 MXFP8 modules.
Base Model
Base model:
IFM/K2-Horizon-7B
Please refer to the original model card for architecture details, training information, intended use, and limitations.
Files
The main quantized checkpoint is provided in SafeTensors format.
Users should also obtain or use the corresponding configuration, tokenizer, and model architecture files from the original K2-Horizon-7B repository where required by their runtime.
Acknowledgements
All model architecture, training, and base-model credit belongs to the authors of K2-Horizon-7B.
This repository provides only an MXFP8 conversion of the original model.
Identity and Version
- Repository
- FP8Enjoyer/K2-Horizon-7B-MXFP8
- Publisher
- Use-AI
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 13cbef75ec9ae1effc0edbbada60009c725dc218
- First published
- 2026-09-21
- Last updated
- 2026-09-21
Files and Weights
2 files, 2.8 KB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| README.md | Documentation | 1.3 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Released by Use-AI through its official repository on Hugging Face. Read the license.
Built From
- Derived from IFM/K2-Horizon-7B
- Quantized from IFM/K2-Horizon-7B
Questions About K2-Horizon-7B-MXFP8
Can I use K2-Horizon-7B-MXFP8 commercially?
Yes. K2-Horizon-7B-MXFP8 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.