Model Intelligence Sheet
nuofang/Qwen3.5-9B-Writing-DPO-GGUF overview
Auto Quantized GGUF Model This repository contains automated GGUF quantization files for nbeerbower/Qwen3.5 9B Writing DPO https://huggingface.co/nbeerbower/Qw…
Runs locally from ~4.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
5 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-9B-Writing-DPO-IQ4_NL.gguf | GGUF | IQ4_NL | 5.05 GB | Download |
| Qwen3.5-9B-Writing-DPO-IQ4_XS.gguf | GGUF | IQ4_XS | 4.84 GB | Download |
| Qwen3.5-9B-Writing-DPO-Q4_K_S.gguf | GGUF | Q4_K_S | 4.98 GB | Download |
| Qwen3.5-9B-Writing-DPO-Q5_K_M.gguf | GGUF | Q5_K_M | 6.02 GB | Download |
| imatrix.gguf | GGUF | GGUF | 4.9 MB | Download |
Model Details
Model README
---
base_model: nbeerbower/Qwen3.5-9B-Writing-DPO
tags:
- llama.cpp
- quantized
- imatrix
---
Auto-Quantized GGUF Model
This repository contains automated GGUF quantization files for nbeerbower/Qwen3.5-9B-Writing-DPO.
The calibration data for the imatrix is targeted at Chinese novels and role-playing (RP), while preserving logic and common sense.
imatrix 的校准数据以中文的小说、角色扮演为目标，同时保留逻辑和常识。
📊 Perplexity Evaluation
(Tested against the provided calibration dataset)
- IQ4_NL: PPL = 11.4488 +/- 0.08750
- IQ4_XS: PPL = 11.4447 +/- 0.08741
Run nuofang/Qwen3.5-9B-Writing-DPO-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models