GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

Koshkasa/DarkArtsForge_Morbid-Miasma-24B-Q4-GGUFs overview

What is that? Standard Q4 K M and Q4 K S quants of DarkArtsForge/Morbid Miasma 24B https://huggingface.co/DarkArtsForge/Morbid Miasma 24B BF16 weights hosted t…

ik_llama.cppggufquantizedllama.cpp4 bitroleplaymixedtext-generationbase_model:DarkArtsForge/Morbid-Miasma-24Bbase_model:quantized:DarkArtsForge/Morbid-Miasma-24Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~12.64 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
DarkArtsForge_Morbid-Miasma-24B-Q4_K_M.ggufGGUFQ4_K_M13.36 GBDownload
DarkArtsForge_Morbid-Miasma-24B-Q4_K_S.ggufGGUFQ4_K_S12.64 GBDownload
DarkArtsForge_Morbid-Miasma-24B-bf16.ggufGGUFBF1643.92 GBDownload

Model Details

Model IDKoshkasa/DarkArtsForge_Morbid-Miasma-24B-Q4-GGUFs
AuthorKoshkasa
Pipelinetext-generation
Licenseapache-2.0
Base modelDarkArtsForge/Morbid-Miasma-24B
Last modified2026-07-29T21:19:55.000Z

Model README

---

license: apache-2.0

base_model:

  • DarkArtsForge/Morbid-Miasma-24B

library_name: ik_llama.cpp

pipeline_tag: text-generation

tags:

  • gguf
  • quantized
  • llama.cpp
  • 4 bit
  • roleplay
  • mixed

quantized_by: Koshkasa

base_model_relation: quantized

---

What is that?

Quant Details

  • vanilla Q4_K_S and Q4_K_M
  • quantized with ik_llama.cpp build: 9d07d868

Cheers

MistralAI - the beloved base model(s).

ikawrakow and contributors of ik_llama.cpp - I probably misused your creation.

DarkArtsForge/Naphula - for the effort of designing and producing the merge. And for reviving my interest in Mistral 24b.

+++ Everyone whose finetunes were included in the merge!

bartowski - for the calibration data + the myriad of quants we all benefit from.

Disclosure

imatrix generated on an intermediary q8_0 quant. I don't eat RAM for breakfast.

My only contribution is compute. This is neither my merge, nor my calibration data. Have fun.

Run Koshkasa/DarkArtsForge_Morbid-Miasma-24B-Q4-GGUFs with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models