Instructions to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF",
	filename="TheDrummer_Skyfall-31B-v4.2-IQ4_KSS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-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 Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

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 Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

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 Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Use Docker

docker model run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

LM Studio
Jan

vLLM

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-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": "Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Ollama
How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with Ollama:
```
ollama run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF
```

Unsloth Studio

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-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 Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-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 Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF to start chatting

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with Docker Model Runner:
```
docker model run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF
```

Lemonade

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Koshkasa/TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF

Run and chat with the model

lemonade run user.TheDrummer_Skyfall-31B-v4.2-IQ4_KSS-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

What's that?

Skyfall is a heavy hitter for mainline consumer GPUs. I used to run it at IQ4_XS on 16 GB with partial offload, which was way too slow.
IQ3_M was tolerable, but restrictive of KVO. IQ3_XXS was permissive of KVO, but too dumbed down.
Whereas the lower precision trellis quant was about squeezing the weights into VRAM together with KV cache, this is a different approach - how much Skyfall can we fit fully into VRAM using SOTA quantization techniques if we aim to run without KV offload?

Turns out, quite a bit.

The goals: shove Skyfall into 16 GB VRAM with system overhead, using ik_llama, hopefully make it all smart enough for a mixed 3-4 bit quant.
The result: a hybrid quantization of TheDrummer/Skyfall-31B-v4.2

Quant Details

iq4_kt: token_embd
iq3_k: ffn_up
iq3_k: ffn_gate
iq4_kss: ffn_down
iq5_k: attn_v, attn_k, attn_q
iq6_k: attn_output, output
imatrix by bartowski

quantized with ik_llama.cpp build: 9d07d868

incompatible with mainline llama.cpp

Rationale

So, we had some byte budget to burn upgrading the v1 trellis quant. It suffered in two key areas - relatively low precision attention, and the massive hit of kicking all ffn down to 3 bits. Thanks to SOTA quantization, it remained functional, but we could do better.
Here we follow the tried Qx_K_M approach of keeping anything directly writing into residuals in highest attainable precision, so attn_output ended up at 6.6 bpw, and ffn_down at 4 bpw. Bumping qkv attention above 5.5 bpw would have diminishing returns at this point, so the rest was spent on shoving some extra bits into ffn_up and ffn_gate, which both recieved a 0.315 bpw uplift to IQ3_K.
attn_output didn't need to be that precise, but the extra bits couldn't meaningfully buff ffn. Bumping ffn_down to iq4_ks fails my criteria due to competing with system overhead, though it remains reasonable with a non-displaying GPU (or not running win)

Cheers

MistralAI - the beloved base model(s).
ikawrakow and contributors of ik_llama.cpp - I probably misused your wonderful creation.
TheDrummer - you cooked a legendary one.
bartowski - for the imatrix + the myriad of quants we all benefit from.