GLM-4.7-Flash-FP8-Dynamic

by kaitchup mit

20 downloads 0 likes on Hugging Face updated 2026-01-23

Model card

This is zai-org/GLM-4.7-Flash quantized with llm-compressor to FP8. The model is compatible with vLLM (tested: v0.14.0). Tested with an L4 (Google Colab).

Developed by: The Kaitchup
License: lfm1.0

Get this model

hp get kaitchup/GLM-4.7-Flash-FP8-Dynamic

The huggingpeers CLI is not released yet. Once it ships, the command above will download the model. Until then, download the weights from Hugging Face.

Details

HuggingPeers ID: ID hpm-QIgtZUPUsdY
Provider: Hugging Face
Revision: 231c5f2e9506
Organization: kaitchup
License: mit
Parameters: 29.9B
Published: 2026-01-23

Files 11

Total size: 54.4 GiB
LFS files: 3
Parameters: 29.9B
Revision: 231c5f2e9506

Browse files & hashes →

Code

GitHub · vllm-project/llm-compressor ↗

Linked from the model card — we do not mirror source repositories.

Sources

Hugging Face · kaitchup/GLM-4.7-Flash-FP8-Dynamic (this) · checked recently

View on Hugging Face ↗