oolfBER/Qwen3.8-27B-UD-Q4_K_XL-single-GGUF overview
Qwen3.8 27B UD Q4 K XL single file GGUF This repository intentionally contains only the exact GGUF used by the Hermes RunPod Serverless worker. Keeping one qua…
Runs locally from ~16.69 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.8-27B-UD-Q4_K_XL.gguf | GGUF | Q4_K_XL | 16.69 GB | Download |
Model Details
Model README
---
license: apache-2.0
base_model: unsloth/Qwen3.8-27B-GGUF
tags:
- gguf
- llama.cpp
- qwen3.8
---
Qwen3.8-27B UD-Q4_K_XL 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:
17,923,394,624bytes - 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.
Run oolfBER/Qwen3.8-27B-UD-Q4_K_XL-single-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models