Instructions to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nubinu/Qwen3.5-4B-MiniFantasy-GGUF",
	filename="F16/Qwen3.5-4B-MiniFantasy-F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with Ollama:
```
ollama run hf.co/Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M
```

Unsloth Studio

How to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Nubinu/Qwen3.5-4B-MiniFantasy-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Nubinu/Qwen3.5-4B-MiniFantasy-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nubinu/Qwen3.5-4B-MiniFantasy-GGUF to start chatting

Docker Model Runner
How to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with Docker Model Runner:
```
docker model run hf.co/Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M
```

Lemonade

How to use Nubinu/Qwen3.5-4B-MiniFantasy-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nubinu/Qwen3.5-4B-MiniFantasy-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-MiniFantasy-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-4B-MiniFantasy — GGUF

GGUF quantizations of Nubinu/Qwen3.5-4B-MiniFantasy — a 4-bit LoRA fine-tune of MuXodious/Qwen3.5-4B-SOMPOA-heresy-v2, focused on multi-turn narrative roleplay, emotional resonance, and character-driven storytelling.

Available Quants

Quantization	Size
Q4_K_M	~2.71 GB
Q5_K_M	~3.07 GB
Q6_K_M	~3.46 GB
Q8_0	~4.48 GB
F16	~8 GB

SillyTavern Setup

Sampler Settings

For best narrative pacing and to prevent repetition, use appropriate RP sampler settings.

General Guide: SillyTavern Sampler Settings Guide
Recommended Preset: Download my recommended sampler JSON here

Character Card Format (`{{description}}` block)

The model was trained on a category-based Markdown structure. For best adherence to personality and lore, structure your character cards like this:

## Identity
- Name: [Full Name]
- Age: [Age]
- Race/Species: [Race]
- Role/Occupation: [Role and relationship]

## Appearance
- [Height, general build]
- [Specific physical features, hair, eyes, etc.]
- Clothing: [Current outfit details]

## Personality
- Public: [Outward facade]
- Private: [True self]
- [1-2 extra bullet points on core personality traits]

## Speech & Quirks
- [Vocal tone and speaking style]
- [Physical habit or nervous tick]
- [How they show affection]

## Backstory & World Context
- [Origin]
- [Key past event]
- [Current situation]

## Goals & Motivations
- Short term: [Immediate goals]
- Long term: [Big picture goals]

About the Base Model

Fine-tuned from: MuXodious/Qwen3.5-4B-SOMPOA-heresy-v2
Full model page: Nubinu/Qwen3.5-4B-MiniFantasy

Downloads last month: 288

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Nubinu/Qwen3.5-4B-MiniFantasy-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

MuXodious/Qwen3.5-4B-SOMPOA-heresy-v2

Finetuned

Nubinu/Qwen3.5-4B-MiniFantasy

Quantized

(2)

this model

Qwen3.5-4B-MiniFantasy — GGUF

Available Quants

SillyTavern Setup

Sampler Settings

Character Card Format ({{description}} block)

About the Base Model

Model tree for Nubinu/Qwen3.5-4B-MiniFantasy-GGUF

Character Card Format (`{{description}}` block)