Instructions to use meshllm/GLM-5.1-MTP-BF16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meshllm/GLM-5.1-MTP-BF16-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="meshllm/GLM-5.1-MTP-BF16-GGUF",
	filename="BF16/GLM-5.1-BF16-00001-of-00306.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 meshllm/GLM-5.1-MTP-BF16-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 meshllm/GLM-5.1-MTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf meshllm/GLM-5.1-MTP-BF16-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshllm/GLM-5.1-MTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf meshllm/GLM-5.1-MTP-BF16-GGUF:BF16

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 meshllm/GLM-5.1-MTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf meshllm/GLM-5.1-MTP-BF16-GGUF:BF16

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 meshllm/GLM-5.1-MTP-BF16-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/GLM-5.1-MTP-BF16-GGUF:BF16

Use Docker

docker model run hf.co/meshllm/GLM-5.1-MTP-BF16-GGUF:BF16

LM Studio
Jan
Ollama
How to use meshllm/GLM-5.1-MTP-BF16-GGUF with Ollama:
```
ollama run hf.co/meshllm/GLM-5.1-MTP-BF16-GGUF:BF16
```

Unsloth Studio

How to use meshllm/GLM-5.1-MTP-BF16-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 meshllm/GLM-5.1-MTP-BF16-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 meshllm/GLM-5.1-MTP-BF16-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meshllm/GLM-5.1-MTP-BF16-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use meshllm/GLM-5.1-MTP-BF16-GGUF with Docker Model Runner:
```
docker model run hf.co/meshllm/GLM-5.1-MTP-BF16-GGUF:BF16
```

Lemonade

How to use meshllm/GLM-5.1-MTP-BF16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/GLM-5.1-MTP-BF16-GGUF:BF16

Run and chat with the model

lemonade run user.GLM-5.1-MTP-BF16-GGUF-BF16

List all available models

lemonade list

GLM-5.1 MTP BF16 GGUF

Reusable high-precision GGUF artifact for the Jianyang Skippy split experiment.

This repo is intended as the expensive one-time conversion boundary:

zai-org/GLM-5.1 safetensors -> BF16 GGUF -> repeated quantization jobs

It is not a promoted runtime quant. Runtime validation happens on downstream quantized artifacts.

Build Metadata

Source repo: zai-org/GLM-5.1
Target repo: meshllm/GLM-5.1-MTP-BF16-GGUF
llama.cpp branch: feat/jianyang-glm51-mtp
llama.cpp commit: 70cc4e16e55465177076f96a18b2bb6a4a44b814
GGUF outtype: bf16
Split max size: 4G
Shard count: 306
Total bytes: 1508010461952

Shard Layout

The artifact is split with --split-max-size 4G. The shard count and file sizes above are generated from the actual conversion output. A smaller split size may be used when the HF bucket mount cannot reliably keep a large GGUF shard open until close.

Downloads last month: 29

GGUF

Model size

754B params

Architecture

glm-dsa

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for meshllm/GLM-5.1-MTP-BF16-GGUF

Base model

zai-org/GLM-5.1

Quantized

(41)

this model