README.md

metadata

base_model:
  - Vortex5/Lunar-Twilight-12B
base_model_relation: quantized
pipeline_tag: text-generation
library_name: safetensors
tags:
  - exl3
  - 4-bit
  - 6-bit
  - 8-bit

Source model

Lunar-Twilight-12B by Vortex5

---

Provided quantized models

ExLlamaV3: release v0.0.18

Type	Size	CLI
H8-4.0BPW	7.49 GB	Copy-paste the line / Download the batch file
H8-6.0BPW	10.22 GB	Copy-paste the line / Download the batch file
H8-8.0BPW	12.95 GB	Copy-paste the line / Download the batch file

Requirements: A python installation with huggingface-hub module to use CLI.

Licensing

License detected: unknown

The license for the provided quantized models is inherited from the source model (which incorporates the license of its original base model). For definitive licensing information, please refer first to the page of the source or base models. File and page backups of the source model are provided below.

---

Backups

Date: 09.01.2026

Source files

Source page (click to expand)

Lunar-Twilight-12B

Overview

Lunar-Twilight-12B was created by merging Starlit-Shadow-12B, Red-Synthesis-12B, Tlacuilo-12B, and Mystic-Matron-12B using a custom method.

Merge configuration

base_model: Vortex5/Starlit-Shadow-12B
models:
  - model: Vortex5/Starlit-Shadow-12B
  - model: Vortex5/Red-Synthesis-12B
  - model: allura-org/Tlacuilo-12B
  - model: Vortex5/Mystic-Matron-12B
merge_method: hpq
chat_template: auto
parameters:
  strength: 0.73
  flavor: 0.36
  steps: 12
  cube_dims: 22
  paradox: 0.43
  boost: 0.56
dtype: bfloat16
tokenizer:
  source: Vortex5/Starlit-Shadow-12B
      

Intended Use

📜 Storytelling

🎭 Roleplay

🌙 Creative Writing