Model Intelligence Sheet
Bigchilli1978/reggie-v3-7b-GGUF overview
language: en license: apache 2.0 base model: Bigchilli1978/reggie v3 7b tags: gguf ollama deepseek r1 qwen reasoning orpo red team blue team REGGIE V3 7B GGUF …
Runs locally from ~7.54 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| reggie_v3_q8.gguf | GGUF | Q8 | 7.54 GB | Download |
Model Details
| Model ID | Bigchilli1978/reggie-v3-7b-GGUF |
|---|---|
| Author | Bigchilli1978 |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Bigchilli1978/reggie-v3-7b |
| Last modified | 2026-10-10T11:45:08.000Z |
Model README
---
language:
- en
license: apache-2.0
base_model: Bigchilli1978/reggie-v3-7b
tags:
- gguf
- ollama
- deepseek-r1
- qwen
- reasoning
- orpo
- red-team
- blue-team
---
REGGIE V3 7B - GGUF Quantized Weights
This repository provides quantized GGUF weights for REGGIE V3 (7B), optimized for execution with Ollama, llama.cpp, and LM Studio.
- Source Model: Bigchilli1978/reggie-v3-7b
- Engineers: The Brothers Brouse (James Brouse & Mike Brouse), Chilliwack, BC, Canada.
- Quantization:
Q8_0(8.09 GB) - near-lossless 8-bit precision.
Quick Start with Ollama
ollama run hf.co/Bigchilli1978/reggie-v3-7b-GGUF:latestRun Bigchilli1978/reggie-v3-7b-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models