Instructions to use zenlm/zen-5-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zenlm/zen-5-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zenlm/zen-5-gguf",
	filename="Huihui-Qwen3.6-35B-A3B-abliterated-ggml-model-Q4_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use zenlm/zen-5-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf zenlm/zen-5-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf zenlm/zen-5-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf zenlm/zen-5-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf zenlm/zen-5-gguf:F16

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 zenlm/zen-5-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf zenlm/zen-5-gguf:F16

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 zenlm/zen-5-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zenlm/zen-5-gguf:F16

Use Docker

docker model run hf.co/zenlm/zen-5-gguf:F16

LM Studio
Jan

vLLM

How to use zenlm/zen-5-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zenlm/zen-5-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": "zenlm/zen-5-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/zenlm/zen-5-gguf:F16

Ollama
How to use zenlm/zen-5-gguf with Ollama:
```
ollama run hf.co/zenlm/zen-5-gguf:F16
```

Unsloth Studio new

How to use zenlm/zen-5-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 zenlm/zen-5-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 zenlm/zen-5-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zenlm/zen-5-gguf to start chatting

Pi new

How to use zenlm/zen-5-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf zenlm/zen-5-gguf:F16

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": "zenlm/zen-5-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zenlm/zen-5-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf zenlm/zen-5-gguf:F16

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 zenlm/zen-5-gguf:F16

Run Hermes

hermes

Docker Model Runner
How to use zenlm/zen-5-gguf with Docker Model Runner:
```
docker model run hf.co/zenlm/zen-5-gguf:F16
```

Lemonade

How to use zenlm/zen-5-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zenlm/zen-5-gguf:F16

Run and chat with the model

lemonade run user.zen-5-gguf-F16

List all available models

lemonade list

Zen5

Canonical default of the Zen5 family. Multimodal sparse MoE (image + text in → text out) with 35B total / 3B active parameters per token, 256K context. The everyday Zen5 model — agentic-trained, fast at scale, frontier-quality vision-language reasoning at a 3B-active compute budget.

Part of the canonical Zen5 ladder:

SKU	Hardware fit	This repo
`zen5-flash`	anything (4 GB VRAM)	zen-5-flash-gguf
`zen5-mini`	32 GB	zen-5-mini-gguf
`zen5` (default)	24 GB+ VRAM (Q4_K)	← you are here
`zen5-pro`	Mac M4 Max / DGX Spark / H100 80GB	zen-5-pro-gguf
`zen5-max`	Mac Studio M3 Ultra 512GB / 8x H100	zen-5-max-gguf

Files

File	Format
main GGUF (`*-Q4_K.gguf`)	GGUF Q4_K (text + vision), refusal-orthogonalized
`mmproj-model-f16.gguf`	multimodal vision projector — load alongside the main GGUF for image input

Run

Hosted via the Hanzo gateway (api.hanzo.ai) as zen5.

Local with llama.cpp (CLI / server) or zen5-engine:

hf download zenlm/zen-5-gguf --local-dir gguf
MAIN=$(ls gguf/*-Q4_K.gguf | head -1)

# text-only chat
llama-cli -m "$MAIN" -p "Explain MoE inference."

# vision-language (image input)
llama-cli -m "$MAIN" \
          --mmproj gguf/mmproj-model-f16.gguf \
          --image path/to/screenshot.png \
          -p "Describe this UI and propose a fix."

Acknowledgements

Built on Qwen/Qwen3.6-35B-A3B (Apache-2.0, multimodal MoE). Abliterated GGUF variant + MTP draft-token support by huihui-ai. Mirrored here for the Zen5 canonical distribution. Native FP8 weights are also available upstream at Qwen/Qwen3.6-35B-A3B-FP8 for higher-precision inference on H100/H200.

Downloads last month: 10

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

Model tree for zenlm/zen-5-gguf

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(405)

this model

Collection including zenlm/zen-5-gguf

Zen5 Chat Ladder

Collection

Canonical Zen5 lineup, smallest to largest. • 6 items • Updated about 20 hours ago