Instructions to use Naphula-Archives/Checkpoint-GGUFs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula-Archives/Checkpoint-GGUFs with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Naphula-Archives/Checkpoint-GGUFs",
	filename="ArceeBlackMagidonia-Q6_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Naphula-Archives/Checkpoint-GGUFs with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Naphula-Archives/Checkpoint-GGUFs:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Naphula-Archives/Checkpoint-GGUFs:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Naphula-Archives/Checkpoint-GGUFs:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Naphula-Archives/Checkpoint-GGUFs:Q6_K

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 Naphula-Archives/Checkpoint-GGUFs:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Naphula-Archives/Checkpoint-GGUFs:Q6_K

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 Naphula-Archives/Checkpoint-GGUFs:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Naphula-Archives/Checkpoint-GGUFs:Q6_K

Use Docker

docker model run hf.co/Naphula-Archives/Checkpoint-GGUFs:Q6_K

LM Studio
Jan
Ollama
How to use Naphula-Archives/Checkpoint-GGUFs with Ollama:
```
ollama run hf.co/Naphula-Archives/Checkpoint-GGUFs:Q6_K
```

Unsloth Studio new

How to use Naphula-Archives/Checkpoint-GGUFs 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 Naphula-Archives/Checkpoint-GGUFs 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 Naphula-Archives/Checkpoint-GGUFs to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Naphula-Archives/Checkpoint-GGUFs to start chatting

Docker Model Runner
How to use Naphula-Archives/Checkpoint-GGUFs with Docker Model Runner:
```
docker model run hf.co/Naphula-Archives/Checkpoint-GGUFs:Q6_K
```

Lemonade

How to use Naphula-Archives/Checkpoint-GGUFs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Naphula-Archives/Checkpoint-GGUFs:Q6_K

Run and chat with the model

lemonade run user.Checkpoint-GGUFs-Q6_K

List all available models

lemonade list

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

Check out the documentation for more information.

Checkpoint GGUFs

Q6 GGUFs and yaml config archives for various checkpoint model tests.

These merges are tests for Goetia & Asmodeus model series.

See https://huggingface.co/Naphula-Archives/ for more models and yaml configs

Update

The series continues with Checkpoints 72 and beyond (previously used A-Z), a series of merges made after patching a broken python library (which was causing mergekit failures)

The recent batch for April 2026 covers C72-84 (all della merges). These are now using IQ4_XS or Q4_0 rather than Q6_K for initial testing.

C72, C73, and C79-81 were deleted. They did not do as well as the others.
C74, C75, C76, C77, C78, C82, C83, and C84 are uploaded in GGUF format.
Additionally there are seperate tests in progress for qliphoth, karcher_stock, and aether merge methods.

Most of these have not been tested throroughly and may exhibit unusual properties or occasional refusals.

Downloads last month: 1,411

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

4-bit

6-bit

Inference Providers NEW

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