Instructions to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers 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-5.3-Flash-UD-Q4_K_XL-layers:BF16
# Run inference directly in the terminal:
llama cli -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16
# Run inference directly in the terminal:
llama cli -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers: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-5.3-Flash-UD-Q4_K_XL-layers:BF16
# Run inference directly in the terminal:
./llama-cli -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers: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-5.3-Flash-UD-Q4_K_XL-layers:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Use Docker

docker model run hf.co/meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

LM Studio
Jan

vLLM

How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Ollama
How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with Ollama:
```
ollama run hf.co/meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16
```
Unsloth Desktop

How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with Docker Model Runner:
```
docker model run hf.co/meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16
```

Lemonade

How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Run and chat with the model

lemonade run user.GLM-5.3-Flash-UD-Q4_K_XL-layers-BF16

List all available models

lemonade list

Hermes Agent

How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

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 meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

GLM-5.3-Flash-UD-Q4_K_XL

Distributed GGUF inference package for Mesh LLM

GGUF layer package for running GLM-5.3-Flash-UD-Q4_K_XL across a local Mesh LLM cluster.

This package is derived from unsloth/GLM-5.3-Flash-GGUF and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

Highlights

Run locally	Pool multiple machines	OpenAI-compatible	Package variant
Private inference on your hardware	Split layers across peers	Serve `/v1/chat/completions` locally	`UD-Q4_K_XL` layer package

Model Overview

Property	Value
Source model	unsloth/GLM-5.3-Flash-GGUF
Model id	`unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL`
Family	GLM
Parameter scale	not recorded
Quantization	`UD-Q4_K_XL`
Layer count	46
Activation width	4096
Package size	188.5 GB
Source file	`UD-Q4_K_XL/GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf`
Package repo	meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers
License	`mit` from unsloth/GLM-5.3-Flash-GGUF

Recommended Use

Local and private inference with Mesh LLM.
Multi-machine serving when the full GGUF is too large for one host.
OpenAI-compatible chat/completions workflows through Mesh LLM's local API.

For upstream architecture details, chat template guidance, sampling recommendations, license terms, and benchmark notes, see the source model card: unsloth/GLM-5.3-Flash-GGUF.

Quickstart

# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers" --split

# Check the mesh and discover the OpenAI-compatible model name.
curl -s http://localhost:3131/api/status
curl -s http://localhost:3131/v1/models

# Send an OpenAI-compatible chat request.
curl -s http://localhost:3131/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL",
    "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
    "max_tokens": 128
  }'

Package Variant

Property	Value
Format	`layer-package`
Canonical source ref	`unsloth/GLM-5.3-Flash-GGUF@ac47690c15c8703615ab7d9c1ef2293d45372757/UD-Q4_K_XL/GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf`
Source revision	`ac47690c15c8703615ab7d9c1ef2293d45372757`
Source SHA-256	`00dceaf3ed08781b1e44513a44ebb19e96248d01ba2a80b17f675a2b6fa9a1ee`
Skippy ABI	`0.1.41`
Package manifest SHA-256	`cebbc901c8daff5c0d0441a8c7f55edeb7a89dcb7d376df11f027b8f348689da`

What Is Included

Artifact	Path	Contents	SHA-256
Manifest	`model-package.json`	Package schema, source identity, checksums	`cebbc901c8daff5c0d0441a8c7f55edeb7a89dcb7d376df11f027b8f348689da`
Metadata	`shared/metadata.gguf`	0 tensors, 9.0 MB	`2d018f5aa91734df4e3e9b7ddaf0449647e60db9c56c621dc7e625f837ca12e1`
Embeddings	`shared/embeddings.gguf`	1 tensors, 651.8 MB	`7d77ffbcd93b2f2ca6647ef2fafdd9ca981b447684dd95db73d0722c339022b0`
Output head	`shared/output.gguf`	2 tensors, 651.8 MB	`21567a02805f462921bf76c47af2f3a3838cf7cedda16ab5449d077de421f57a`
Transformer layers	`layers/layer-*.gguf`	46 layer artifacts, 1409 tensors, 185.1 GB	`see model-package.json`
Projector	`projectors/mmproj-BF16.gguf`	mmproj projector, 1.1 GB	`513c9bfc55898998186543caefc01626fb28e378b92f391018e1c3dd6655b113`
Projector	`projectors/mmproj-F16.gguf`	mmproj projector, 1.1 GB	`96ccc182997646ad4405385a1987b1ac1e6adccd2669de43c3ea39692699ed27`

Validation

Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref main. Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.

skippy-model-package write-package "/source/UD-Q4_K_XL/GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_GLM-5.3-Flash-UD-Q4_K_XL-layers-1/package"

Model tree for meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers

Base model

zai-org/GLM-5.3-Flash

Quantized

unsloth/GLM-5.3-Flash-GGUF

Quantized

(1)

this model

meshllm
/

GLM-5.3-Flash-UD-Q4_K_XL-layers

GLM-5.3-Flash-UD-Q4_K_XL

Highlights

Model Overview

Recommended Use

Quickstart

Package Variant

What Is Included

Validation

Links

Model tree for meshllm/GLM-5.3-Flash-UD-Q4_K_XL-layers