Source model
NeutralGear-24B-V.2 by OddTheGreat
Provided quantized models
ExLlamaV3: release v0.0.18
| Type | Size | CLI |
|---|---|---|
| H8-4.0BPW | 13.16 GB | Copy-paste the line / Download the batch file |
| H8-6.0BPW | 18.72 GB | Copy-paste the line / Download the batch file |
| H8-8.0BPW | 24.27 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: 19.01.2026
Source page (click to expand)
NeutralGear_24B_V.2
This is a merge of pre-trained language models
Goal of this merge was to create model, capable to true neutral or dark and extremely unsafe styles of roleplay.
Subgoal was to have good erp capabilities.
It seems, this time goals were reached.
Model is stable, follows given formatting, smart and creative enough. Instructions are followed good.
Lenght of replies is medium, not too short, not too long.
Also, i noticed that model has good attention to char card and context, for 24b mistral.
Ru is supported.
Tested on Mistral- tekken v7 preset, modified shingane v.1 sysprompt. T0.81, XTC 0.1 0.1.
Model tree for DeathGodlike/OddTheGreat_NeutralGear-24B-V.2_EXL3
Base model
OddTheGreat/NeutralGear_24B_V.2