Modelpublic

oolfBER/Qwen3.8-27B-UD-Q4_K_XL-single-GGUF

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

4likes1.9kdownloads

Model Card

Qwen3.8-27B UD-Q4KXL single-file GGUF

This repository intentionally contains only the exact GGUF used by the Hermes RunPod Serverless worker. Keeping one quantization here prevents RunPod cached-model provisioning from downloading every quantization in the upstream repository.

—Upstream: unsloth/Qwen3.8-27B-GGUF
—Upstream revision: fdd03b8bbd279c1694563650e79d85a2373d9934
—File: Qwen3.8-27B-UD-Q4_K_XL.gguf
—Size: 17,923,394,624 bytes
—SHA-256: bee238bbeb3dc0a34bde4d0dedbaee1f98c009e8bb4226f03070054c12fb1372

The model and quantization remain under the upstream Apache-2.0 license and attribution. This repository does not modify the model weights.