Instructions to use unsloth/GLM-5.3-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from WinGet (Windows)

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

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 unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL

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 unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/GLM-5.3-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/GLM-5.3-Flash-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": "unsloth/GLM-5.3-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL

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

How to use unsloth/GLM-5.3-Flash-GGUF with Pi:

Start the llama.cpp server

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

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": "unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use unsloth/GLM-5.3-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.GLM-5.3-Flash-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/GLM-5.3-Flash-GGUF with Hermes Agent:

Start the llama.cpp server

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

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 unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/GLM-5.3-Flash-GGUF with OpenClaw:

Start the llama.cpp server

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

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 "unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL" \
  --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"

New discussion

Resources

View closed (1)

GLM-5.3-Flash now runs 1.6-3.4 faster! ⚡

pinned

🔥 17

#18 opened about 2 months ago by

danielhanchen

You can now Run GLM-5.3-Flash Locally! ✨

pinned

🚀👍 14

#4 opened about 2 months ago by

danielhanchen

UD-Q3_K_XL split across two DGX Sparks (llama.cpp RPC over RDMA): memory, speed, 10 users, and what tripped me up

#28 opened 7 days ago by

faysalabdulaziz

Strix Halo (395/8060S) results: ~29 tok/s with MTP on Vulkan, quant/flag notes

#27 opened 8 days ago by

j2ipper

bf16

#26 opened 17 days ago by

smailimohammad

Is a warning about unused tensors expected?

#25 opened 17 days ago by

finding1

Upstream tensor naming

➕ 2

#24 opened 23 days ago by

2002c07525c77c06

glm now 2-4 times faster new llama fork. 2 3090 now from 12 to 24t/s

#23 opened 27 days ago by

neuralll

UD-IQ4_XS on 64 GB RAM + one 5090: ~250 t/s prefill, ~6 t/s decode by streaming experts from 2 NVMe SSDs

#22 opened 29 days ago by

xMytze

I tried Q3 version with new patched of llama.cpp, but get /////////// loop

#21 opened about 1 month ago by

linhcnguyen

How to deploy to Inference Endpoints?

#20 opened about 1 month ago by

michael-newsrx-com

Shard_Rewrite mmproj is one key behind PR #27773

👍 1

#19 opened about 2 months ago by

ht-test

Would suggest a UD-IQ4_K_M for easier running on 256gb devices.

#17 opened about 2 months ago by

ResonML

Is MTP not implemented by your patch?

#16 opened about 2 months ago by

Cypherfox

Folks with smaller VRAM but enough RAM - Token per second almost doubled for Q3 (unsloth)

👀 1

#15 opened about 2 months ago by

nizoai

IQ1_XXS Quants

#14 opened about 2 months ago by

Banaxi-Tech

Will you provide the NVFP4 version ?

👍 1

#13 opened about 2 months ago by

ahmedessamsaeed

Why is IQ1 and IQ2 almost the same size?

#12 opened about 2 months ago by

ghostplant

GLM5.3-Flash at Q2?

#11 opened about 2 months ago by

Dino-Fan-1

All GLM-5.3-Flash quants are now available.

🔥 4

#10 opened about 2 months ago by

danielhanchen

1 bit lower

👍 1

#9 opened about 2 months ago by

Banaxi-Tech

Normal k-quants?

👍 2

#8 opened about 2 months ago by

NovNovikov

Any ETA on the 5bit quants?

👍 2

#7 opened about 2 months ago by

JPFlare

67?

😔 11

#6 opened about 2 months ago by

bgt5yg4g

Will you upload the imatrix ?

👍 2

#5 opened about 2 months ago by

AliceThirty

Q8 lossless quants

👍 1

#3 opened about 2 months ago by

Bacruru

Finetuned

#2 opened about 2 months ago by

smailimohammad