Instructions to use zenlm/zen5-max-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zenlm/zen5-max-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zenlm/zen5-max-gguf",
	filename="DeepSeek-V4-Pro-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-Instruct-imatrix.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use zenlm/zen5-max-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 zenlm/zen5-max-gguf
# Run inference directly in the terminal:
llama cli -hf zenlm/zen5-max-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zenlm/zen5-max-gguf
# Run inference directly in the terminal:
llama cli -hf zenlm/zen5-max-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 zenlm/zen5-max-gguf
# Run inference directly in the terminal:
./llama-cli -hf zenlm/zen5-max-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 zenlm/zen5-max-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zenlm/zen5-max-gguf

Use Docker

docker model run hf.co/zenlm/zen5-max-gguf

LM Studio
Jan

vLLM

How to use zenlm/zen5-max-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zenlm/zen5-max-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zenlm/zen5-max-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zenlm/zen5-max-gguf

Ollama
How to use zenlm/zen5-max-gguf with Ollama:
```
ollama run hf.co/zenlm/zen5-max-gguf
```

Unsloth Studio

How to use zenlm/zen5-max-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/zen5-max-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/zen5-max-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/zen5-max-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use zenlm/zen5-max-gguf with Docker Model Runner:
```
docker model run hf.co/zenlm/zen5-max-gguf
```

Lemonade

How to use zenlm/zen5-max-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zenlm/zen5-max-gguf

Run and chat with the model

lemonade run user.zen5-max-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Zen5 Max

Top tier of the Zen5 family. The full-Pro base, asymmetrically quantized (routed IQ2_XXS up/gate, Q2_K down; shared experts, attention projections, routing logits and the LM head left at higher precision).

Repackaged from deepseek-ai/DeepSeek-V4-Pro (mit, DeepSeek) — quantized to GGUF from the abliterated variant by huihui-ai. Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.

Use when you have 512 GB+ unified memory (Mac Studio M3 Ultra 512 GB) or an 8x H100 / H200 pool and want the deepest reasoning quality in the family. For 128 GB hardware, use zenlm/zen-5-pro-gguf instead.

Part of the canonical Zen5 ladder:

SKU	Hardware fit	This repo
`zen5-flash`	anything	zen-5-flash-gguf
`zen5-mini`	32 GB	zen-5-mini-gguf
`zen5` (default)	24 GB+ VRAM	zen-5-gguf
`zen5-pro`	128 GB single-machine	zen-5-pro-gguf
`zen5-max`	512 GB Mac Studio / 8x H100	← you are here

Files

File pattern	Size	Quant
main GGUF (`-IQ2XXS-w2Q2K--Instruct-imatrix.gguf`)	432 GB	routed `IQ2_XXS` + `Q2_K`, shared `Q8_0`, attn `Q8_0`, imatrix-tuned

Run

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

Local with the zen5-engine:

git clone https://github.com/zenlm/zen5-engine
cd zen5-engine && make                  # macOS Metal
                       # or: make cuda-generic for multi-H100

hf download zenlm/zen-5-max-gguf --local-dir gguf
ln -sf "$(ls gguf/*-Instruct-imatrix.gguf | head -1)" zen5max.gguf
./zen5 -m zen5max.gguf -p "Explain MoE inference."
./zen5-server -m zen5max.gguf --ctx 1000000 --kv-disk-dir /tmp/zen5-kv --kv-disk-space-mb 16384

License

apache-2.0 (this packaging). Upstream: deepseek-ai/DeepSeek-V4-Pro by DeepSeek, licensed MIT; abliterated variant by huihui-ai. This repository redistributes a quantized derivative; the upstream MIT terms are retained.