hayulalab/Dragon-32B-Q4_K_M-GGUF overview
تنين / Dragon 32B Q4 K M GGUF 32B Parameter Model — Trained from scratch on Arabic + English data. | Property | Value | |: |: | | Architecture | Qwen3 32B | | …
Runs locally from ~18.40 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| dragon-qwen3-32b-8900-Q4_K_M.gguf | GGUF | Q4_K_M | 18.40 GB | Download |
Model Details
| Model ID | hayulalab/Dragon-32B-Q4_K_M-GGUF |
|---|---|
| Author | hayulalab |
| Pipeline | text-generation |
| License | other |
| Base model | — |
| Last modified | 2026-07-02T13:43:15.000Z |
Model README
---
license: other
license_name: hayula-research-license-v1
license_link: https://hayula.xyz/license
language:
- ar
- en
tags:
- dragon
- 32b
- qwen3
- arabic
- bilingual
- hayula
- gguf
pipeline_tag: text-generation
---
تنين / Dragon-32B-Q4_K_M-GGUF
32B Parameter Model — Trained from scratch on Arabic + English data.
| Property | Value |
|:---------|:------|
| Architecture | Qwen3-32B |
| Training | From scratch, 8,900 iterations |
| Quantization | Q4_K_M GGUF |
| Size | 18GB |
Usage (llama.cpp)
./llama-cli -m dragon-qwen3-32b-8900-Q4_K_M.gguf -p "Your prompt here" -n 512License
Hayula Research License v1.0
Run hayulalab/Dragon-32B-Q4_K_M-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models