Instructions to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-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 Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

Use Docker

docker model run hf.co/Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

LM Studio
Jan

vLLM

How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

Ollama
How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF with Ollama:
```
ollama run hf.co/Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE
```
Unsloth Desktop

How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF with Docker Model Runner:
```
docker model run hf.co/Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE
```

Lemonade

How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

Run and chat with the model

lemonade run user.Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF-MXFP4_MOE

List all available models

lemonade list

Hermes Agent

How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE

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/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF:MXFP4_MOE" \
  --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"

What's that?

MXFP4_MOE quantization of Vortex5/G4-Midnight-Macaw-26B-A4B

Use case

Running the model on consumer-grade Blackwell GPUs (due to native fp4 support).
Running on other hardware IS POSSIBLE. I lack conclusive data to say if it's a good idea.

Benchmarks

Measurement	Q4_K_S (imatrix)	MXFP4_MOE (default, 8 exps)	delta	MXFP4_MOE (16 exps)	delta	MXFP4_MOE (24 exps)	delta
pp512	3067.83	3567.72	+16.29%	2783.90	-9.26%	TBD	TBD
tg128	108	89.87	-16.79%	76.43	-29.23%	TBD	TBD
pp65536	1748.64	2219.20	+26.91%	1789.84	+2.36%	TBD	TBD
tg1024	87.81	88.97	+1.20%	67.38	-23.26%	TBD	TBD
pp65536 + tg1024 wall time (s)	49.14	41.03	-16.5%	51.81	+5.43%	TBD	TBD
hellaswag% (s=42, n=400, greedy)	56.5%	61.00%	+7.96%	64.00%	+13.27%	63.5%	+12.39%
hellaswag (s=42, n=400, greedy)	226	244	+18	256	+30	254	+28
winogrande% (n=1267, greedy)	59.51%	57.38%	-3.58%	64.17%	+7.83%	66.45%	+11.66%
winogrande (n=1267, greedy)	754	727	-27	813	+59	842	+88
Size (bytes)	15464827008	14727180640	-4.77%	14727180640	-4.77%	14727180640	-4.77%

tested on: --temp 0 -ngl 999 -b 512 -ub 512 -ctk q8_0 -ctv q8_0
pp65536/tg1024 test for Q4_K_S was run at -ngl 29 instead - it did not fit otherwise.
pp65536/tg1024 test for MXFP4_MOE(16 exps) was run at -ngl 30 instead - it did not fit otherwise.

Conclusion

MXFP4_MOE allows either Q4_K_S intelligence at -16.5% wall time, or higher than Q4_K_S intelligence at the cost of +5.43% wall time (with experts/tok override to 16), while being of smaller file size.
Is it worth it? I don't know. At this point, my particular config isn't compute-limited, but rather bottlenecked by PCI-E. WYSIWYG.

Disclosure

My only contribution is compute. This is not my merge. Have fun.

Cheers

Google - the base model.
Vortex5 - for the merge effort.
Everyone whose finetunes were included in the merge!

Downloads last month: 46

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for Koshkasa/Vortex5_G4-Midnight-Macaw-26B-A4B-MXFP4_MOE-GGUF

Base model

Vortex5/G4-Midnight-Macaw-26B-A4B

Quantized

(5)

this model