gabrielmtzcarrillo/qwen3-4b-heretic-gguf overview
Qwen3 4B Heretic GGUF Derived from Qwen/Qwen3 4B Instruct 2507 https://huggingface.co/Qwen/Qwen3 4B Instruct 2507 . The source weights were locally modified be…
Runs locally from ~2.33 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | gabrielmtzcarrillo/qwen3-4b-heretic-gguf |
|---|---|
| Author | gabrielmtzcarrillo |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-4B-Instruct-2507 |
| Last modified | 2026-09-30T21:09:15.000Z |
Model README
---
license: apache-2.0
base_model: Qwen/Qwen3-4B-Instruct-2507
pipeline_tag: text-generation
tags:
- gguf
---
Qwen3 4B Heretic GGUF
Derived from Qwen/Qwen3-4B-Instruct-2507. The source weights were locally modified before GGUF conversion.
Licensed under Apache License 2.0, matching the base model.
Modifications and files
This repository contains F16 and Q4_K_M GGUF conversions. Conversion and quantization were performed with llama.cpp (commit 5f436dd). The GGUF files differ from the original upstream weight files in format and, for Q4_K_M, quantization.
Run gabrielmtzcarrillo/qwen3-4b-heretic-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models