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

KeinNiemand/Kuwutu-7B-CYOA-IK-GGUF-v2 overview

Kuwutu 7B CYOA IK GGUF v2 IK specific GGUF quantizations of Kuwutu 7B CYOA v2 https://huggingface.co/KeinNiemand/Kuwutu 7B CYOA v2?not for all audiences=true ,…

ggufquantizationik_llama.cppqwen2chatmlinteractive-fictioncyoansfwexplicitnot-for-all-audiencestext-generationenbase_model:KeinNiemand/Kuwutu-7B-CYOA-v2base_model:quantized:KeinNiemand/Kuwutu-7B-CYOA-v2license:cc-by-nc-4.0endpoints_compatibleregion:usimatrixconversational

Runs locally from ~2.63 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation

Repository Files & Downloads

8 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Kuwutu-7B-CYOA-v2-IQ2_KL.ggufGGUFIQ2_KL2.63 GBDownload
Kuwutu-7B-CYOA-v2-IQ3_K.ggufGGUFIQ3_K3.23 GBDownload
Kuwutu-7B-CYOA-v2-IQ4_K.ggufGGUFIQ4_K4.17 GBDownload
Kuwutu-7B-CYOA-v2-IQ4_KS.ggufGGUFIQ4_KS3.97 GBDownload
Kuwutu-7B-CYOA-v2-IQ4_KSS.ggufGGUFIQ4_KSS3.77 GBDownload
Kuwutu-7B-CYOA-v2-IQ5_K.ggufGGUFIQ5_K4.96 GBDownload
Kuwutu-7B-CYOA-v2-IQ5_KS.ggufGGUFIQ5_KS4.77 GBDownload
Kuwutu-7B-CYOA-v2-IQ6_K.ggufGGUFIQ6_K5.89 GBDownload

Model Details

Model IDKeinNiemand/Kuwutu-7B-CYOA-IK-GGUF-v2
AuthorKeinNiemand
Pipelinetext-generation
Licensecc-by-nc-4.0
Base modelKeinNiemand/Kuwutu-7B-CYOA-v2
Last modified2026-07-15T08:55:44.000Z

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

- ik_llama.cpp

- qwen2

- chatml

- interactive-fiction

- cyoa

- nsfw

- explicit

- not-for-all-audiences

---

Kuwutu-7B-CYOA-IK-GGUF-v2

IK-specific GGUF quantizations of Kuwutu-7B-CYOA-v2, a model for CYOA-style interactive fiction.

These files require ikawrakow/ik_llama.cpp. For mainline-compatible files, use Kuwutu-7B-CYOA-GGUF-v2.

See the full model card for model details.

Files

  • Kuwutu-7B-CYOA-v2-IQ6_K.gguf
  • Kuwutu-7B-CYOA-v2-IQ5_K.gguf
  • Kuwutu-7B-CYOA-v2-IQ5_KS.gguf
  • Kuwutu-7B-CYOA-v2-IQ4_K.gguf
  • Kuwutu-7B-CYOA-v2-IQ4_KS.gguf
  • Kuwutu-7B-CYOA-v2-IQ4_KSS.gguf
  • Kuwutu-7B-CYOA-v2-IQ3_K.gguf
  • Kuwutu-7B-CYOA-v2-IQ2_KL.gguf

The quantizations use an importance matrix generated from representative project calibration text.

Run KeinNiemand/Kuwutu-7B-CYOA-IK-GGUF-v2 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