Instructions to use unsloth/GLM-4.6-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/GLM-4.6-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/GLM-4.6-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/GLM-4.6-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/GLM-4.6-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/GLM-4.6-GGUF",
	filename="BF16/GLM-4.6-BF16-00001-of-00015.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 unsloth/GLM-4.6-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/GLM-4.6-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/GLM-4.6-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/GLM-4.6-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/GLM-4.6-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-4.6-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/GLM-4.6-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-4.6-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/GLM-4.6-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/GLM-4.6-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/GLM-4.6-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/GLM-4.6-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-4.6-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/GLM-4.6-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/GLM-4.6-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 "unsloth/GLM-4.6-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": "unsloth/GLM-4.6-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 "unsloth/GLM-4.6-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": "unsloth/GLM-4.6-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/GLM-4.6-GGUF with Ollama:
```
ollama run hf.co/unsloth/GLM-4.6-GGUF:UD-Q4_K_XL
```

Unsloth Studio new

How to use unsloth/GLM-4.6-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 unsloth/GLM-4.6-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 unsloth/GLM-4.6-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/GLM-4.6-GGUF to start chatting

Pi new

How to use unsloth/GLM-4.6-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/GLM-4.6-GGUF:UD-Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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-4.6-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/GLM-4.6-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/GLM-4.6-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-4.6-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/GLM-4.6-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/GLM-4.6-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/GLM-4.6-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/GLM-4.6-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.GLM-4.6-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Fingers crossed for the 4.6-air

by aaron-newsome - opened Sep 30, 2025

Discussion

aaron-newsome

Sep 30, 2025

4.6 is a bit too big for my setup so I sincerely hope they drop a 4.6-air variant.

bobig

Oct 1, 2025

This comment has been hidden

bobig

Oct 1, 2025

bobig

Oct 1, 2025

Sorry, no love for the Poors from ZAI

Maybe Unsloth will quant an IQ2-XSS, it worked well for 4.5

Downtown-Case

Oct 1, 2025

•

edited Oct 1, 2025

You might try the ik_llama.cpp quants from ubergarm and such when they come out, though they only run with the ik server due to its custom quantization types. GLM 4.5 works good in 128GB RAM (+ a single GPU) with them.

...Would the unsloth guys be interested in this? Maybe combining it with whatever dynamic script y'all use? The KL and KT trellis quant types really do help a ton in that ~3bpw range.

x-polyglot-x

Oct 1, 2025

@Downtown-Case

What quant do you run with ik_llama.cpp on the 128gb machine? I have a PC with that configuration with an AMD gpu. I also have an m4 max with 128gb memory. GLM-4.5 was always very slow for some reason, much slower than other similar-sized models. I'd be curious to know what kind of speeds you get with those custom quants.

danielhanchen

Unsloth AI org Oct 1, 2025

Sorry, no love for the Poors from ZAI

Maybe Unsloth will quant an IQ2-XSS, it worked well for 4.5

We fixed multiple issues with the chat template, the 2bit is out now, the rest will come in the next few hours!

Rotating

Oct 1, 2025

Them not releasing an AIR version serves everyone right for complaining about GLM 4.5 when using the AIR version and not specifying it.

puchuu

Oct 2, 2025

•

edited Oct 2, 2025

I am using IQ2_XXS on a machine with 5950x, 128GB RAM, and 7600XT 16GB VRAM. It works, the result is good but performance is low. AIR version will be much better. I am offloading as much layers as possible to the GPU using llama.cpp.

PS I've disabled thinking by appending '/nothink' at the end of prompt and it allowed to use GLM 4.6 somehow. Example:

llama_perf_sampler_print:    sampling time =      55.64 ms /  9635 runs   (    0.01 ms per token, 173176.12 tokens per second)
llama_perf_context_print:        load time =   13348.83 ms
llama_perf_context_print: prompt eval time =  454403.14 ms /  9173 tokens (   49.54 ms per token,    20.19 tokens per second)
llama_perf_context_print:        eval time =  236910.60 ms /   461 runs   (  513.91 ms per token,     1.95 tokens per second)
llama_perf_context_print:       total time =  691481.59 ms /  9634 tokens
llama_perf_context_print:    graphs reused =        458
llama_memory_breakdown_print: | memory breakdown [MiB]           | total   free      self    model   context   compute    unaccounted |
llama_memory_breakdown_print: |   - ROCm0 (Radeon™ RX 7600 XT) | 16368 =  146 + ( 15519 =   5884 +    8712 +     923) +         701 |
llama_memory_breakdown_print: |   - Host                         |                 112062 = 108553 +    3432 +      76                |

bobig

Oct 4, 2025

This Distill from 4.6 to AIR is working:

https://huggingface.co/BasedBase/GLM-4.5-Air-GLM-4.6-Distill

puchuu

Oct 7, 2025

I've tried BasedBase/GLM-4.5-Air-GLM-4.6-Distill and found its quality is not enough. Also, it hanged. IQ2_XXS of GLM-4.6 is better.

Rotating

Oct 7, 2025

Now people are going to talk about this distill as if it's the real thing. Sad!

Rotating

Oct 8, 2025

I've tried BasedBase/GLM-4.5-Air-GLM-4.6-Distill and found its quality is not enough. Also, it hanged. IQ2_XXS of GLM-4.6 is better.

From what I've heard, it's literally just glm-4.5-Air renamed or something.

puchuu

Oct 8, 2025

From what I've heard, it's literally just glm-4.5-Air renamed or something.

I was using glm-4.5-air from unsloth for a long time, from my experience BasedBase/GLM-4.5-Air-GLM-4.6-Distillis different. It is some sort of distil but it is pretty bad.

bobig

Oct 24, 2025

•

edited Oct 24, 2025

more compression, cerebras is smashing:

https://huggingface.co/cerebras/GLM-4.6-REAP-218B-A32B-FP8

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment