KeinNiemand/Kuwutu-7B-CYOA-GGUF-v2 overview
Kuwutu 7B CYOA GGUF v2 Mainline llama.cpp compatible GGUF quantizations of Kuwutu 7B CYOA v2 https://huggingface.co/KeinNiemand/Kuwutu 7B CYOA v2?not for all a…
Runs locally from ~2.67 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Kuwutu-7B-CYOA-v2-IQ2_M.gguf | GGUF | IQ2_M | 2.67 GB | Download |
| Kuwutu-7B-CYOA-v2-IQ3_M.gguf | GGUF | IQ3_M | 3.42 GB | Download |
| Kuwutu-7B-CYOA-v2-IQ4_XS.gguf | GGUF | IQ4_XS | 3.97 GB | Download |
| Kuwutu-7B-CYOA-v2-Q3_K_M.gguf | GGUF | Q3_K_M | 3.59 GB | Download |
| Kuwutu-7B-CYOA-v2-Q4_K_M.gguf | GGUF | Q4_K_M | 4.37 GB | Download |
| Kuwutu-7B-CYOA-v2-Q5_K_M.gguf | GGUF | Q5_K_M | 5.08 GB | Download |
| Kuwutu-7B-CYOA-v2-Q6_K.gguf | GGUF | Q6_K | 5.83 GB | Download |
| Kuwutu-7B-CYOA-v2-Q8_0.gguf | GGUF | Q8_0 | 7.55 GB | Download |
| Kuwutu-7B-CYOA-v2-bf16.gguf | GGUF | BF16 | 14.20 GB | Download |
Model Details
| Model ID | KeinNiemand/Kuwutu-7B-CYOA-GGUF-v2 |
|---|---|
| Author | KeinNiemand |
| Pipeline | text-generation |
| License | cc-by-nc-4.0 |
| Base model | KeinNiemand/Kuwutu-7B-CYOA-v2 |
| Last modified | 2026-07-15T08:39:51.000Z |
Model README
---
base_model: KeinNiemand/Kuwutu-7B-CYOA-v2
base_model_relation: quantized
license: cc-by-nc-4.0
pipeline_tag: text-generation
language:
- en
tags:
- gguf
- quantization
- qwen2
- chatml
- interactive-fiction
- cyoa
- nsfw
- explicit
- not-for-all-audiences
---
Kuwutu-7B-CYOA-GGUF-v2
Mainline llama.cpp-compatible GGUF quantizations of Kuwutu-7B-CYOA-v2, a model for CYOA-style interactive fiction.
See the full model card for model details.
Files
Kuwutu-7B-CYOA-v2-bf16.ggufKuwutu-7B-CYOA-v2-Q8_0.ggufKuwutu-7B-CYOA-v2-Q6_K.ggufKuwutu-7B-CYOA-v2-Q5_K_M.ggufKuwutu-7B-CYOA-v2-Q4_K_M.ggufKuwutu-7B-CYOA-v2-Q3_K_M.ggufKuwutu-7B-CYOA-v2-IQ4_XS.ggufKuwutu-7B-CYOA-v2-IQ3_M.ggufKuwutu-7B-CYOA-v2-IQ2_M.gguf
The quantizations use an importance matrix generated from representative project calibration text.
Run KeinNiemand/Kuwutu-7B-CYOA-GGUF-v2 with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models