Instructions to use pixelmelt/Incelgpt-24B_v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pixelmelt/Incelgpt-24B_v1.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pixelmelt/Incelgpt-24B_v1.1",
	filename="Incelgpt-24B_v1.1_GGUF-F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use pixelmelt/Incelgpt-24B_v1.1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pixelmelt/Incelgpt-24B_v1.1:F16
# Run inference directly in the terminal:
llama-cli -hf pixelmelt/Incelgpt-24B_v1.1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pixelmelt/Incelgpt-24B_v1.1:F16
# Run inference directly in the terminal:
llama-cli -hf pixelmelt/Incelgpt-24B_v1.1:F16

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 pixelmelt/Incelgpt-24B_v1.1:F16
# Run inference directly in the terminal:
./llama-cli -hf pixelmelt/Incelgpt-24B_v1.1:F16

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 pixelmelt/Incelgpt-24B_v1.1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pixelmelt/Incelgpt-24B_v1.1:F16

Use Docker

docker model run hf.co/pixelmelt/Incelgpt-24B_v1.1:F16

LM Studio
Jan
Ollama
How to use pixelmelt/Incelgpt-24B_v1.1 with Ollama:
```
ollama run hf.co/pixelmelt/Incelgpt-24B_v1.1:F16
```

Unsloth Studio new

How to use pixelmelt/Incelgpt-24B_v1.1 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 pixelmelt/Incelgpt-24B_v1.1 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 pixelmelt/Incelgpt-24B_v1.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pixelmelt/Incelgpt-24B_v1.1 to start chatting

Docker Model Runner
How to use pixelmelt/Incelgpt-24B_v1.1 with Docker Model Runner:
```
docker model run hf.co/pixelmelt/Incelgpt-24B_v1.1:F16
```

Lemonade

How to use pixelmelt/Incelgpt-24B_v1.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pixelmelt/Incelgpt-24B_v1.1:F16

Run and chat with the model

lemonade run user.Incelgpt-24B_v1.1-F16

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Incelgpt

Heard of GPT4-Chan? Same deal, has been known to act like an anxty andrew tate follower. Dont use instruct, use any mistral 24b sampler settings, dont name the bot "assistant"

Characters with no description have the most unhinged responses

Blog Post

A Q4_K_M is available

As always, the author is not responsible for what you do with this model.

Sampler

try "mistral small 24b.json" in this repo, high temps .7 are better for unhinged responses.

Downloads last month: 17

Safetensors

Model size

22B params

Tensor type

BF16

Inference Providers NEW

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

Collection including pixelmelt/Incelgpt-24B_v1.1

Incelgpt v1.1

Collection

Hates everyone, itself, and spouts misinformation • 2 items • Updated Sep 2, 2025