base_model: prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption
library_name: gguf
license: apache-2.0
tags:
- gguf
- qwen3.5
- vision
- webllm
- webgpu
⚡ PocketWeights: Gliese-Qwen3.5-9B-Abliterated-WebGGUF
Heavy models, made light. We specialize in high-quality GGUF quantizations optimized for edge devices and gaming laptops.
What is this model?
This is an optimized GGUF of prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption. It is a highly capable 9B vision-language model, abliterated for unrestricted image captioning.
🌐 Why these specific formats? (WebGPU & Legacy Support)
While modern K-quants exist for this model, we explicitly generated these Q4_0 and Q5_0 files for developers building browser-based AI (WebLLM/WebGPU) and users on older hardware. These older formats offer maximum cross-platform compatibility where standard K-quants often fail or crash shaders.
📦 Pick Your Hardware
Q4_0: 🔥 Fits 6GB VRAM: The standard choice for WebLLM browser deployment. | Size: 4.9485 GiBQ4_1: 🔥 Fits 6GB VRAM: The standard choice for WebLLM browser deployment. | Size: 5.4104 GiBQ5_0: 💻 Fits 8GB VRAM: Higher precision for legacy AVX hardware. | Size: 5.8723 GiBQ5_1: 💻 Fits 8GB VRAM: Higher precision for legacy AVX hardware. | Size: 6.3342 GiB
🚀 Quick Start (Ollama)
Run this model instantly in your terminal:
ollama run hf.co/PocketWeights/Gliese-Qwen3.5-9B-Abliterated-WebGGUF:Q4_0