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

Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic overview

L3.1 Dark Reasoning LewdPlay evo Hermes R1 Uncensored 8B GGUF heretic This repository contains GGUF format quantizations of the model using llama.cpp . 3/100 R…

gguftext-generation-inferencellama-cppheretictext-generationbase_model:NousResearch/Hermes-3-Llama-3.1-8Bbase_model:quantized:NousResearch/Hermes-3-Llama-3.1-8Blicense:otherendpoints_compatibleregion:usconversational

Runs locally from ~4.58 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation

Repository Files & Downloads

4 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q4_K_M.ggufGGUFGGUF4.58 GBDownload
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q5_K_M.ggufGGUFGGUF5.34 GBDownload
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q6_K.ggufGGUFGGUF6.14 GBDownload
L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q8_0.ggufGGUFGGUF7.95 GBDownload

Model Details

Model IDYingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic
AuthorYingyaeliae
Pipelinetext-generation
Licenseother
Base modelNousResearch/Hermes-3-Llama-3.1-8B
Last modified2026-06-25T08:46:04.000Z

Model README

---

license: other

base_model: NousResearch/Hermes-3-Llama-3.1-8B

tags:

  • text-generation-inference
  • llama-cpp
  • gguf
  • heretic

pipeline_tag: text-generation

quantized_by: llama.cpp

---

L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic

This repository contains GGUF format quantizations of the model using llama.cpp.

3/100 Refusal via Heretic 1.4 by https://github.com/p-e-w/heretic

Available Quants:

  • Q4_K_M: 4-bit medium quantization (balanced performance/size).
  • Q5_K_M: 5-bit medium quantization (recommended sweet spot for 8B).
  • Q6_K: 6-bit quantization (extremely close to unquantized quality).
  • Q8_0: 8-bit standard quantization.

How to use with llama.cpp:

./llama-cli -m L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic.Q5_K_M.gguf -n 512 -ngl 999 -co -i

Run Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF-heretic 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