Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1-GGUF overview
Nyx RP Mini 2.6B Instruct 2608 v0.1: A tiny model that inherited writing style of much bigger models 5190867860606097818 https://cdn uploads.huggingface.co/pro…
Runs locally from ~1.56 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Nyx-RP-Mini-2.6B-Instruct-2608-v0.1.BF16.gguf | GGUF | GGUF | 5.03 GB | Download |
| Nyx-RP-Mini-2.6B-Instruct-2608-v0.1.Q4_K_M.gguf | GGUF | GGUF | 1.56 GB | Download |
| Nyx-RP-Mini-2.6B-Instruct-2608-v0.1.Q5_K_M.gguf | GGUF | GGUF | 1.81 GB | Download |
| Nyx-RP-Mini-2.6B-Instruct-2608-v0.1.Q6_K.gguf | GGUF | GGUF | 2.07 GB | Download |
| Nyx-RP-Mini-2.6B-Instruct-2608-v0.1.Q8_0.gguf | GGUF | GGUF | 2.68 GB | Download |
Model Details
| Model ID | Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1-GGUF |
|---|---|
| Author | Indexnusrefather |
| Pipeline | text-generation |
| License | other |
| Base model | LiquidAI/LFM2.5-2.6B |
| Last modified | 2026-08-17T12:47:17.000Z |
Model README
---
license: other
license_name: lfm1.0
license_link: LICENSE
pipeline_tag: text-generation
tags:
- GGUF
- instruct
- thinking removed
- no thinking
- instruct only
- creative writing
- RP
- Roleplay
- creative
- writer
- ERP
- v0.1
- early version
- experimental
- edge
- lfm2.5
- finetune
- Unsloth
- Reasoning disabled
- No reasoning
- SillyTavern
- SLM
- Mini
- Small Language Model
- Quantized
language:
- en
base_model:
- LiquidAI/LFM2.5-2.6B
base_model_relation: finetune
library_name: transformers
---
Nyx-RP-Mini-2.6B-Instruct-2608-v0.1: A tiny model that inherited writing style of much bigger models!
-
"Does high quality and engaging roleplay, even at its smallest!"
---
Quick Overview:
What was done:
- Thinking was fully removed
- Writing and narrative consistency was improved
- Performance over long roleplay sessions was improved
- Stability and model intelligence was fully maintained
Quants(This time quants and safetensor files will be in DIFFERENT repos!):
- BF16: Overkill
- Q8_0: Highest quality
- Q6_K: Very high quality, lossless
- Q5_K_M: Very high quality, near lossless
- Q4_K_M: Decent quality, fast
Creator Note:
I think I will release a next version sooner or later, this is only my first attempt, I will also work on expanding my dataset soon.
Run Indexnusrefather/Nyx-RP-Mini-2.6B-Instruct-2608-v0.1-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models