Iloqt/Barcenas-StyleTune-31B-Fable-GGUF overview
license: apache 2.0 library name: gguf base model: Iloqt/Barcenas StyleTune 31B Fable base model relation: quantized tags: gguf gemma4 gemma 4 31B merge lm hea…
Runs locally from ~11.53 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Barcenas-StyleTune-31B-Fable-Q2_K.gguf | GGUF | Q2_K | 11.53 GB | Download |
| Barcenas-StyleTune-31B-Fable-Q3_K_M.gguf | GGUF | Q3_K_M | 14.80 GB | Download |
| Barcenas-StyleTune-31B-Fable-Q4_K_M.gguf | GGUF | Q4_K_M | 18.14 GB | Download |
| Barcenas-StyleTune-31B-Fable-Q5_K_M.gguf | GGUF | Q5_K_M | 21.25 GB | Download |
| Barcenas-StyleTune-31B-Fable-Q6_K.gguf | GGUF | Q6_K | 24.55 GB | Download |
| Barcenas-StyleTune-31B-Fable-Q8_0.gguf | GGUF | Q8_0 | 31.79 GB | Download |
Model Details
Model README
---
license: apache-2.0
library_name: gguf
base_model: Iloqt/Barcenas-StyleTune-31B-Fable
base_model_relation: quantized
tags:
- gguf
- gemma4
- gemma-4
- 31B
- merge
- lm_head-graft
- creative writing
- roleplay
- conversational
---
Done by request, enjoy.
Barcenas-StyleTune-31B-Fable (GGUF)
GGUF quants of Iloqt/Barcenas-StyleTune-31B-Fable: a text-only Gemma 4 31B with Danielbrdz/Barcenas-31b-Fable as the base and the lm_head grafted from Gryphe/Gemma-4-31B-StyleTune.
Quants
Q2_K, Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0 — standard K-quants.
Notes
- Run with the Gemma 4 chat template.
- Benefits from repetition penalty or DRY to avoid token loops.
Run Iloqt/Barcenas-StyleTune-31B-Fable-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models