Instructions to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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_Shadow-Siren-26B-A4B-APEX-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_Shadow-Siren-26B-A4B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF

Use Docker

docker model run hf.co/Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF

LM Studio
Jan

vLLM

How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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_Shadow-Siren-26B-A4B-APEX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF

Ollama
How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF with Ollama:
```
ollama run hf.co/Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF
```

Unsloth Studio

How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF to start chatting

How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF
```

Lemonade

How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF

Run and chat with the model

lemonade run user.Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Koshkasa/Vortex5_Shadow-Siren-26B-A4B-APEX-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_Shadow-Siren-26B-A4B-APEX-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/Vortex5_Shadow-Siren-26B-A4B-APEX-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"

What's that?

As denoted by its creators, APEX is "a novel MoE-aware mixed-precision quantization technique for llama.cpp". I suggest reading their information on the how and why of the method.

These two GGUFs are APEX quantizations of Vortex5/Shadow-Siren-26B-A4B, using EmanuelOverride's custom APEX recipe, HarmonicMinus, and a minor customization of that edit to cap shared ffn at Q6_K and replace Q4_K and Q4_0 (which was a fallback for ffn_down_exps from Q3_K) sparse expert quants with MXFP4. Both recipes use mradermacher's imatrix found here

To quote EmanuelOverride regarding the philosophy behind HarmonicMinus:

🎵 The Harmonic Series (Pulsed Attention)

Following on from the Harmonic Resonance branch, the Harmonic layouts further optimize layer contiguity for performance, by following strict precision tiers across all 30 layers (High/Medium/Low), while priorizing high-precision tiers for Global Attention (GA) layers, preventing aggressive compression in order to anchor deep-context tracking.

i-Harmonic.Minus: 14,369.74 MiB (4.78 BPW) — High-performance configuration. Condenses the architecture into 3 strict tiers (5/15/10). Shifts high-precision blocks to coincide with global attention pulses.

My modification, aptly named HarmonicMinusMinus, retains most of the original recipe and adheres to the same philosophy, sacrificing some precision on sparse experts FFN layers for extra VRAM savings, while retaining global attention-focused attn distribution. A secondary effect is minor speedup on GPUs with native fp4 support. The HarmonicMinusMinus modification APEX recipe is provided.

Benchmarks

Measurement	HarmonicMinus	HarmonicMinusMinus	Delta
pp512	2764.56	3233.05	+16.97%
tg128	106.81	112.63	+5.45%
pp32768	2378.52	2543.86	+6.95%
tg512	102.54	103.86	+1.29%
pp32768 + tg512 wall time (s)	18.76	17.81	-5.06%
hellaswag% (s=42, n=400, greedy)	52.25%	52.25%	==
hellaswag (s=42, n=400, greedy)	209	209	==
winogrande% (n=1267, greedy)	55.09%	57.06%	+1.97% (abs)
winogrande (n=1267, greedy)	698	723	+25
Size (bytes)	15083595360	14157258080	-6.14%
Bits per weight	4.78	4.48	-0.3

pp32768/tg512 tests were run at q4_0/q4_0 cache quantization to ensure both models fully fit in VRAM with KV cache on my GPU.

Conclusion

WYSIWYG. MXFP4 is lower precision than Q4_K and can underrepresent outliers. For certain ffn_down_exps it may have had an impact that had not been identified during my surface testing. Feedback welcome.

Disclosure

My only contribution is compute and a little tinkering with an already existing custom APEX recipe. This is neither my merge, nor my quantization methodology. Have fun.

Cheers

Google - the base model.
Vortex5 - for the merge effort.
Everyone whose finetunes were included in the merge!
mudler - for the APEX quantization methodology.
EmanuelOverride - for the custom APEX experiments and the base recipe.
mradermacher - for the imatrix + myriads of quants we all benefit from.