Instructions to use mradermacher/Seed-X-Instruct-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Seed-X-Instruct-7B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Seed-X-Instruct-7B-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Seed-X-Instruct-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Seed-X-Instruct-7B-GGUF",
	filename="Seed-X-Instruct-7B.IQ4_XS.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 mradermacher/Seed-X-Instruct-7B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M

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 mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M

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 mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Seed-X-Instruct-7B-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Seed-X-Instruct-7B-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 mradermacher/Seed-X-Instruct-7B-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 mradermacher/Seed-X-Instruct-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Seed-X-Instruct-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mradermacher/Seed-X-Instruct-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Seed-X-Instruct-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Seed-X-Instruct-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Seed-X-Instruct-7B-GGUF-Q4_K_M

List all available models

lemonade list

Please refer to the official documentation for specific usage instructions

by YuLu0713 - opened Jul 21, 2025

Discussion

YuLu0713

Jul 21, 2025

@mradermacher Hi~ Thanks for your interests on Seed-X. We noticed that you have released the quantitative version of Seed-X, but due to significant fluctuations in the model's performance after quantification, it has affected many people who are interested in trying it out.

Please add the following line to the readme: Quantized models are unstable. Please refer to the official documentation for specific usage instructions (https://huggingface.co/ByteDance-Seed/Seed-X-PPO-7B#quickstart). We will soon release an official quantized model. Thanks a lot.

mradermacher

Owner Jul 21, 2025

Neither the link nor anything else provides any evidence that quantisations are somehow "fluctuating". Quantisation does affect the quality, and low bit quants are known to have significant quality degradations.

To the contrary, it looks as if seed-x models have quality issues, as normal inferencing results in nans.

So let's not add unevidenced claims to the README - the model should simply stand on its own.

If you want to publish your own official quantisation, that is wonderful, btw. :=)

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