CoolFace
Modelpublic

SergiusFlavius/Qwen3-VL-8B-Instruct-heretic-gguf

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face
1likes181downloads
Model Card

Qwen3-VL-8B-Instruct-heretic-gguf

Overview

This repository provides a GGUF quantized builds of Qwen3-VL-8B-Instruct-heretic for llama.cpp.

This model is a decensored derivative of the official Qwen/Qwen3-VL-8B-Instruct, modified using Heretic v1.1.0.

Quantization Details

  • —Backend: llama.cpp
  • —Commit: 7537 (e68c19b0f)
  • —Method: Q4_K_M for weights, FP16 for multimodal adapter
  • —Imatrix Optimization: [x]️ (custom dataset)