Instructions to use v102ss/Alice-Qwopus3.5-9B-RP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use v102ss/Alice-Qwopus3.5-9B-RP-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf v102ss/Alice-Qwopus3.5-9B-RP-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 v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf v102ss/Alice-Qwopus3.5-9B-RP-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 v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use v102ss/Alice-Qwopus3.5-9B-RP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "v102ss/Alice-Qwopus3.5-9B-RP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v102ss/Alice-Qwopus3.5-9B-RP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M

Ollama
How to use v102ss/Alice-Qwopus3.5-9B-RP-GGUF with Ollama:
```
ollama run hf.co/v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use v102ss/Alice-Qwopus3.5-9B-RP-GGUF with Docker Model Runner:
```
docker model run hf.co/v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M
```

Lemonade

How to use v102ss/Alice-Qwopus3.5-9B-RP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull v102ss/Alice-Qwopus3.5-9B-RP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Alice-Qwopus3.5-9B-RP-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Alice Qwopus3.5 9B RP GGUF

This is an Alice RP release based on loilkon/Qwopus3.5-9B-v3.5-Uncensored Q4_K_M.

No model weights were changed. The GGUF tokenizer.chat_template includes a default Alice system prompt for runtimes that honor GGUF chat templates.

Files

File	Description
`Alice-Qwopus3.5-9B-RP-Q4_K_M.gguf`	Q4_K_M GGUF release with Alice identity prompt in chat template

Expected Behavior

If asked who it is, the model should answer as Alice.
If asked whether it is Qwen, the model should keep the conversation identity as Alice instead of explaining model lineage.
Adult consensual RP openness is preserved from the original Qwopus GGUF.

Usage

Use a GGUF-compatible runtime that respects the embedded chat template, such as LM Studio or llama.cpp conversation mode.

llama-cli \
  -m Alice-Qwopus3.5-9B-RP-Q4_K_M.gguf \
  -cnv \
  --temp 0.75 \
  --top-p 0.9 \
  --repeat-penalty 1.0

Recommended Runtime Settings

Use chat/conversation mode.
Respect model chat template.
Temperature around 0.6-0.9 for RP.
Repeat penalty close to 1.0.

Limitations

This is not a LoRA or full fine-tune.
Apps that override or ignore tokenizer.chat_template may not apply the Alice identity prompt.
User-provided system prompts can still change behavior depending on runtime precedence.
The release is intended for local text-generation and roleplay experimentation. Users are responsible for complying with applicable laws and platform policies.