Instructions to use unsloth/Hunyuan-A13B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Hunyuan-A13B-Instruct-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/Hunyuan-A13B-Instruct-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/Hunyuan-A13B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Hunyuan-A13B-Instruct-GGUF",
	filename="BF16/Hunyuan-A13B-Instruct-BF16-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Hunyuan-A13B-Instruct-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 unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use unsloth/Hunyuan-A13B-Instruct-GGUF with Ollama:
```
ollama run hf.co/unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Hunyuan-A13B-Instruct-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 unsloth/Hunyuan-A13B-Instruct-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 unsloth/Hunyuan-A13B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Hunyuan-A13B-Instruct-GGUF to start chatting

How to use unsloth/Hunyuan-A13B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

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": "unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Hunyuan-A13B-Instruct-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 unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

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 unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use unsloth/Hunyuan-A13B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Hunyuan-A13B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Hunyuan-A13B-Instruct-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Hunyuan-A13B-Instruct-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Sampling parameters from the github

by YearZero - opened Jul 8, 2025

Discussion

YearZero

Jul 8, 2025

•

edited Jul 8, 2025

Just in case this is helpful in the absence of official recommended sampling parameters, here's what I found in the repo:

Sampling parameters are listed for inference with this model in several files.

Default Parameters
The default sampling parameters for the model are specified in the models/generation_config.json file. These include:

{
  "temperature": 0.7,
  "top_k": 20,
  "top_p": 0.8,
  "repetition_penalty": 1.05
}

Inference Examples
You can find these parameters being used in various scripts:

In agent/excel_demo/demo.py and agent/mcp_demo/demo.py, the client.chat.completions.create method is called with:
```
{
  "temperature": 0.5,
  "top_k": 20,
  "top_p": 0.7,
  "repetition_penalty": 1.05
}
```

In examples/eval_demo_vllm.py, the parameters are:

{
  "temperature": 0.7,
  "top_k": 20,
  "top_p": 0.6,
  "repetition_penalty": 1.05
}

In inference/openapi.sh, a curl command uses:

{
  "temperature": 0.7,
  "top_k": 20,
  "top_p": 0.6,
  "repetition_penalty": 1.05
}

YearZero

Jul 8, 2025

•

edited Jul 8, 2025

EDIT: Right now the only way to stop it from thinking in llama-server is with /no_think (I tested someone else's gguf).

Also, it looks to have hybrid-reasoning just like Qwen:

Our model defaults to using slow-thinking reasoning, and there are two ways to disable CoT reasoning:

Pass enable_thinking=False when calling apply_chat_template.

Adding /no_think before the prompt will force the model not to use CoT reasoning. Similarly, adding /think before the prompt will force the model to perform CoT reasoning.

Besides using /no_think and /think, if it works just like Qwen in llama-server, you should be able to disable reasoning like this:

--jinja ^
--reasoning-budget 0 ^
--reasoning-format none ^

And to enable it:

--jinja ^
--reasoning-budget -1 ^
--reasoning-format none ^

But I will have to test it to be absolutely sure once we have the quants up :)

P.S. - I'm just providing this to hopefully help with your "how to run Hunyuan" page, if you plan to make one for this bad boy, and should you choose to use any of this info for the page at all.

danielhanchen

Unsloth AI org Jul 9, 2025

I made quants sorry on the delay - I was confirming why the model had a huge perplexity score (180 upwards). I verifed the quants we just uploaded should be fine. Please use:

./llama.cpp/llama-cli -hf unsloth/Hunyuan-A13B-Instruct-GGUF:Q4_K_XL -ngl 99 --jinja --temp 0.7 --top-k 20 --top-p 0.8 --repeat-penalty 1.05

shimmyshimmer

Unsloth AI org Jul 9, 2025

Btw guys we uploaded the GGUFs now!

CC: @YearZero @owao @engrtipusultan @itsthenewmeta

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment