AliceThirty/G4-Alice-v1.0-31B-gguf overview
<div style="display: flex; align items: flex start; gap: 20px;" <img src="https://cdn uploads.huggingface.co/production/uploads/63283c7ecbc744f197047b4a/R8FtVq…
Runs locally from ~11.10 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| BF16/G4-Mero-Serenity-31B-bf16.gguf | GGUF | BF16 | 57.20 GB | Download |
| Q2_K/G4-Mero-Serenity-31B-Q2_K.gguf | GGUF | Q2_K | 11.10 GB | Download |
| Q3_K/G4-Mero-Serenity-31B-Q3_K.gguf | GGUF | Q3_K | 14.24 GB | Download |
| Q3_K_L/G4-Mero-Serenity-31B-Q3_K_L.gguf | GGUF | Q3_K_L | 15.49 GB | Download |
| Q3_K_M/G4-Mero-Serenity-31B-Q3_K_M.gguf | GGUF | Q3_K_M | 14.24 GB | Download |
| Q3_K_S/G4-Mero-Serenity-31B-Q3_K_S.gguf | GGUF | Q3_K_S | 12.82 GB | Download |
| Q4_K/G4-Mero-Serenity-31B-Q4_K.gguf | GGUF | Q4_K | 17.40 GB | Download |
| Q4_K_M/G4-Mero-Serenity-31B-Q4_K_M.gguf | GGUF | Q4_K_M | 17.40 GB | Download |
| Q4_K_S/G4-Mero-Serenity-31B-Q4_K_S.gguf | GGUF | Q4_K_S | 16.54 GB | Download |
| Q5_K/G4-Mero-Serenity-31B-Q5_K.gguf | GGUF | Q5_K | 20.35 GB | Download |
| Q5_K_M/G4-Mero-Serenity-31B-Q5_K_M.gguf | GGUF | Q5_K_M | 20.35 GB | Download |
| Q5_K_S/G4-Mero-Serenity-31B-Q5_K_S.gguf | GGUF | Q5_K_S | 19.85 GB | Download |
| Q6_K/G4-Mero-Serenity-31B-Q6_K.gguf | GGUF | Q6_K | 23.47 GB | Download |
| Q8_0/G4-Mero-Serenity-31B-Q8_0.gguf | GGUF | Q8_0 | 30.39 GB | Download |
Model Details
| Model ID | AliceThirty/G4-Alice-v1.0-31B-gguf |
|---|---|
| Author | AliceThirty |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | AliceThirty/G4-Alice-v1.0-31B |
| Last modified | 2026-06-18T17:33:04.000Z |
Model README
---
datasets:
- zerofata/Instruct-Anime
- zerofata/Gemini-3.1-Pro-GLM5-Characters
- zerofata/Gemini-3.1-Pro-SmallWiki
base_model:
- AliceThirty/G4-Alice-v1.0-31B
pipeline_tag: text-generation
license: apache-2.0
---
<div style="display: flex; align-items: flex-start; gap: 20px;">
<img src="https://cdn-uploads.huggingface.co/production/uploads/63283c7ecbc744f197047b4a/R8FtVqy5K9cp1uwzTlMJf.png" width="150" height="auto" />
<div>I like <a href="https://huggingface.co/zerofata/G4-MeroMero-31B">MeroMero</a>, but it's too censored and not HORNY enough. So I tried to merge it with <a href="https://huggingface.co/ReadyArt/Serenity-31B">Serenity</a> (which I declare is the horniest model ever made). After many many tries, I came to the conclusion that these models couldn't be merged. It always produced gibberish. So I changed my plans and decided to retrain MeroMero (as I understand their training) but with Serenity as a base. It seems to have worked well, so I am sharing my first attempt with you.
Please tell me what you think. Is it clever? Does it have a good long term memory? Is it uninhibited? Sloppy?
It's my first fine-tune, so any feedback is welcome!
The fine tune was done on a single rtx 5090 thanks to unsloth, with a lora rank of 80, for one epoch, and a low learning rate not to override Serenity (but maybe I should have choosen an even lower learning rate).
</div></div>
Run AliceThirty/G4-Alice-v1.0-31B-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models