Casual-Autopsy_RP-Spectrum-24B_EXL3

Source model

RP-Spectrum-24B by Casual-Autopsy

---

Provided quantized models

ExLlamaV3: release v0.0.20

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: 03.02.2026

Source files

<details> <summary>Source page (click to expand)</summary>

RP-Spectrum-24B

<img src="https://huggingface.co/Casual-Autopsy/RP-Spectrum-24B/resolve/main/RP-Spectrum.png">

A merge of some of the best RP finetunes the community has to offer.

Merge Details

Merge Method

This model was merged using the DELLA merge method using mistralai/Mistral-Small-3.2-24B-Instruct-2506 as a base.

Models Merged

The following models were included in the merge:

• mistralai/Mistral-Small-3.2-24B-Instruct-2506
• zerofata/MS3.2-PaintedFantasy-v3-24B
• TheDrummer/Cydonia-24B-v4
• ReadyArt/Dark-Nexus-24B-v2.0
• Gryphe/Codex-24B-Small-3.2
• Doctor-Shotgun/MS3.2-24B-Magnum-Diamond

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-Small-3.2-24B-Instruct-2506

  - model: zerofata/MS3.2-PaintedFantasy-v3-24B # Pink/Red
    parameters:
      weight: 0.3
      density: 1.0
      epsilon: 0.0
  - model: TheDrummer/Cydonia-24B-v4 # Black
    parameters:
      weight: 0.3
      density: 0.4
      epsilon: 0.25
  - model: CrucibleLab/M3.2-24B-Loki-V1.3 # Green
    parameters:
      weight: 0.3
      density: 0.4
      epsilon: 0.25
  - model: Gryphe/Codex-24B-Small-3.2 # Blue (Yes, blue. Fuck you.)
    parameters:
      weight: 0.3
      density: 0.4
      epsilon: 0.25
  - model: ReadyArt/Dark-Nexus-24B-v2.0 # Orange
    parameters:
      weight: 0.3
      density: 0.4
      epsilon: 0.25
  - model: Doctor-Shotgun/MS3.2-24B-Magnum-Diamond # White
    parameters:
      weight: 0.3
      density: 0.4
      epsilon: 0.25

# Seed: 199803
merge_method: della
parameters:
  lambda: 0.9
  normalize: true
  int8_mask: false
base_model: mistralai/Mistral-Small-3.2-24B-Instruct-2506
dtype: float32
out_dtype: bfloat16

tokenizer:
  source: zerofata/MS3.2-PaintedFantasy-v3-24B

</details>