Instructions to use tensorblock/YuLan-Mini-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/YuLan-Mini-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tensorblock/YuLan-Mini-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/YuLan-Mini-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/YuLan-Mini-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/YuLan-Mini-GGUF",
	filename="YuLan-Mini-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tensorblock/YuLan-Mini-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/YuLan-Mini-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/YuLan-Mini-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/YuLan-Mini-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/YuLan-Mini-GGUF:Q2_K

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 tensorblock/YuLan-Mini-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/YuLan-Mini-GGUF:Q2_K

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 tensorblock/YuLan-Mini-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/YuLan-Mini-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/YuLan-Mini-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/YuLan-Mini-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/YuLan-Mini-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": "tensorblock/YuLan-Mini-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/YuLan-Mini-GGUF:Q2_K

SGLang

How to use tensorblock/YuLan-Mini-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/YuLan-Mini-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/YuLan-Mini-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/YuLan-Mini-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/YuLan-Mini-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use tensorblock/YuLan-Mini-GGUF with Ollama:
```
ollama run hf.co/tensorblock/YuLan-Mini-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/YuLan-Mini-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 tensorblock/YuLan-Mini-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 tensorblock/YuLan-Mini-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use tensorblock/YuLan-Mini-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/YuLan-Mini-GGUF:Q2_K
```

Lemonade

How to use tensorblock/YuLan-Mini-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/YuLan-Mini-GGUF:Q2_K

Run and chat with the model

lemonade run user.YuLan-Mini-GGUF-Q2_K

List all available models

lemonade list

yulan-team/YuLan-Mini - GGUF

This repo contains GGUF format model files for yulan-team/YuLan-Mini.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template


<s>

    <|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|>

    <|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|>

    <|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename	Quant type	File Size	Description
YuLan-Mini-Q2_K.gguf	Q2_K	1.468 GB	smallest, significant quality loss - not recommended for most purposes
YuLan-Mini-Q3_K_S.gguf	Q3_K_S	1.463 GB	very small, high quality loss
YuLan-Mini-Q3_K_M.gguf	Q3_K_M	1.560 GB	very small, high quality loss
YuLan-Mini-Q3_K_L.gguf	Q3_K_L	1.606 GB	small, substantial quality loss
YuLan-Mini-Q4_0.gguf	Q4_0	1.463 GB	legacy; small, very high quality loss - prefer using Q3_K_M
YuLan-Mini-Q4_K_S.gguf	Q4_K_S	1.746 GB	small, greater quality loss
YuLan-Mini-Q4_K_M.gguf	Q4_K_M	1.846 GB	medium, balanced quality - recommended
YuLan-Mini-Q5_0.gguf	Q5_0	1.742 GB	legacy; medium, balanced quality - prefer using Q4_K_M
YuLan-Mini-Q5_K_S.gguf	Q5_K_S	1.882 GB	large, low quality loss - recommended
YuLan-Mini-Q5_K_M.gguf	Q5_K_M	1.969 GB	large, very low quality loss - recommended
YuLan-Mini-Q6_K.gguf	Q6_K	2.580 GB	very large, extremely low quality loss
YuLan-Mini-Q8_0.gguf	Q8_0	2.580 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/YuLan-Mini-GGUF --include "YuLan-Mini-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/YuLan-Mini-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 67

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

Model tree for tensorblock/YuLan-Mini-GGUF

Base model

yulan-team/YuLan-Mini

Quantized

(13)

this model

Datasets used to train tensorblock/YuLan-Mini-GGUF

Evaluation results

pass@1 on HumanEval
self-reported

0.640
pass@1 on MBPP
self-reported

0.659
maj@1 on MATH-500
self-reported

0.378
maj@1 on GSM8K
self-reported

0.684