---

language:

• en

license: gemma

license_link: https://ai.google.dev/gemma/docs/gemma_4_license

library_name: gguf

pipeline_tag: text-generation

base_model:

• darthcrawl/Lilith-31B-v1.0

base_model_relation: quantized

tags:

• roleplay
• creative-writing
• gemma
• gemma4
• qlora
• uncensored
• nsfw
• not-for-all-audiences
• gguf
• llama.cpp

---

<p align="center"><img src="lilith.png" width="480" alt="Lilith"/></p>

Lilith-31B-v1.0 (GGUF)

Versatile uncensored roleplay / creative-writing model on Gemma-4-31B. Drives any character card (SillyTavern / pluma), built to be lively and varied rather than flat or repetitive. darthcrawl. Explicit-capable.

• Base: coder3101/gemma-4-31B-it-heretic (decensored Gemma-4-31B-it)
• Method: QLoRA r32/alpha64 all-linear, loss masked to model turns, 1 epoch eval-driven. Release = the ~0.39-epoch checkpoint (eval 2.11 vs base 7.03), picked over the fully-trained one to keep prose lively (loss != liveliness).
• Data: ~30M tokens, 8 curated sources (human forum RP, AO3, curated public RP, curated synth), ~40/60 NSFW/SFW.
• Chat template: Gemma-4 (<|turn>user ... <turn|> / <|turn>model ...).
• Sampling tip: DRY + XTC + modest repetition penalty for max variety.

Siblings: Lilith-31B-v1.0 (bf16) | -LoRA | -GGUF | -MLX-4bit/6bit/8bit

Quants

| File | Size | Notes |

|---|---|---|

| Q3_K_M | 15.3 GB | tight VRAM |

| Q4_K_M | 18.7 GB | balanced |

| Q5_K_M | 21.8 GB | |

| Q6_K | 25.2 GB | fits 32GB w/ --cache-type-k/v q8_0 |

| Q8_0 | 32.6 GB | near-lossless |

| IQ4_XS | 16.7 GB | imatrix, best quality-per-GB at 4-bit |

| IQ3_M | 14.4 GB | imatrix, tightest usable VRAM |

IQ quants use a register-calibrated imatrix (3MB of held-out corpus prose, imat_register.dat in this repo). Serve with llama.cpp --jinja.