Instructions to use tensorblock/Mengzi3-8B-Chat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/Mengzi3-8B-Chat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/Mengzi3-8B-Chat-GGUF",
	filename="Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/Mengzi3-8B-Chat-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/Mengzi3-8B-Chat-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/Mengzi3-8B-Chat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/Mengzi3-8B-Chat-GGUF:Q2_K

Ollama
How to use tensorblock/Mengzi3-8B-Chat-GGUF with Ollama:
```
ollama run hf.co/tensorblock/Mengzi3-8B-Chat-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-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/Mengzi3-8B-Chat-GGUF to start chatting

Docker Model Runner
How to use tensorblock/Mengzi3-8B-Chat-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/Mengzi3-8B-Chat-GGUF:Q2_K
```

Lemonade

How to use tensorblock/Mengzi3-8B-Chat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/Mengzi3-8B-Chat-GGUF:Q2_K

Run and chat with the model

lemonade run user.Mengzi3-8B-Chat-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e2b102261b765c587446489dab02321472610ebb81ae240b21d5e81725c1f737
-size 4321956608

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63783b3391b0b075e3b92b253d03ffddd28c1f877df4a7862b04087c1a8a2e64
-size 4018918144

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f434b13d12af3a1c1b180b36236d717c5722d05e3d7c33b494cc44a164417f4
-size 3664499456

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b2849ef0576fedbd322d47a72d93f5659e2936e7611779a6107d80bc4f53302
-size 4661211904

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:313554018972ae6fac09c795052ba1fd344764100d56644dc54c9ef5a7ac63e4
-size 4920734464

tensorblock
/

Mengzi3-8B-Chat-GGUF

Remove .gguf files (keep Q2_K.gguf)