Instructions to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF with Trellis:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF

Use Docker

docker model run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF

LM Studio
Jan

vLLM

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF

Ollama
How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF with Ollama:
```
ollama run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF
```
Unsloth Desktop

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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_16G-checkerboard-trellis-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF with Docker Model Runner:
```
docker model run hf.co/Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF
```

Lemonade

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF

Run and chat with the model

lemonade run user.TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-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_16G-checkerboard-trellis-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Koshkasa/TheDrummer_Skyfall-31B-v4.2_16G-checkerboard-trellis-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_16G-checkerboard-trellis-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_16G-checkerboard-trellis-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"

!!! quantized for use with ik_llama.cpp and its derivatives !!!

!!! incompatible with mainline llama.cpp as of commit #34af94c !!!

What's that?

Skyfall is a heavy hitter for mainline consumer GPUs. I have an abusive relationship with it - the goal of fitting the most of it into 16 GBs of VRAM, even without KVO, eluded me twice. I made two publicly avaliable ik_llama.cpp-exclusive quants of Skyfall before, each with their own issues. Lessons were learned. Most were forgotten.

It's time for Round 3.

The goal: shove Skyfall into 16 GB VRAM with system overhead, AGAIN, using ik_llama, hopefully make it all smart enough for a mixed quant.
The result: another hybrid quantization of TheDrummer/Skyfall-31B-v4.2, hopefully the final iteration

Rationale

Having a very limited budget for a 31b model (I run the system off the same GPU I use for ik_llama.cpp inference, so I am only safe within a 14.5 GB margin), I decided to play chess - literally. The recipe involves two layer precision schemae. The higher precision schema was used in 8 edge layers, and as every third middle layer as a drift prevention checkpoint.
The idea is simple. Keeping edge layers in higher precision should stabilize input comprehension/output composition (keeping them as unharmed as we can afford, given the size limits), and having checkpoints in an otherwise aggressive mixed 3/4bit ffn flow should let the model compensate for SOME quantization-borne drift. That, together with ik's advancements with trellis quantization and a bulkier imatrix dataset with an expanded RP corpus should keep the model sane. In theory.
Will it have a measurable mechanistic effect? Will such a ratio of layers be enough? Idk. That's an experiment and a love letter to Skyfall at the same time.

Quant Recipe

Input

⋯13–48

Output

Input / Output Higher Precision Lower Precision

Embeddings

token_embd

iq6_k

High-Precision Blocks

attn_k	iq5_k
attn_q	iq5_k
attn_v	iq6_k
attn_output	iq6_k
ffn_up	iq4_kt
ffn_gate	iq4_kt
ffn_down	iq4_kt
attn_norm / ffn_norm	f32

Low-Precision Blocks

attn_k	iq4_kt
attn_q	iq4_kt
attn_v	iq6_k
attn_output	iq4_kt
ffn_up	iq3_kt
ffn_gate	iq3_kt
ffn_down	iq4_kt
attn_norm / ffn_norm	f32

lm_head

output

iq6_k

Pattern: Blocks 0–3 high · Middle: 2 low + 1 high repeating · Blocks 51–54 high · Total: 54 layers

imatrix generated using bartowski's combined dataset coupled with a random conversation 200k-token prune of Squish42/bluemoon-fandom-1-1-rp-cleaned.

quantized with ik_llama.cpp as of commit 43afea46c25a12aae6db1e3105643267164898b4 (Fri Aug 14 07:55:11 2026 +0200)

Cheers

MistralAI - the beloved base model(s).
ikawrakow and contributors of ik_llama.cpp - I probably misused your creation.
TheDrummer - you cooked a legendary one.
bartowski - for the combined dataset + the myriad of quants we all benefit from.
EmanuelOverride - for sparking my interest in custom quantization as a concept.