Instructions to use unsloth/GLM-4.7-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/GLM-4.7-Flash-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/GLM-4.7-Flash-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/GLM-4.7-Flash-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/GLM-4.7-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/GLM-4.7-Flash-GGUF",
	filename="BF16/GLM-4.7-Flash-BF16-00001-of-00002.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-4.7-Flash-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-4.7-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/GLM-4.7-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-server -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/GLM-4.7-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-4.7-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/GLM-4.7-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-4.7-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/GLM-4.7-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-4.7-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-4.7-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/GLM-4.7-Flash-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-4.7-Flash-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-4.7-Flash-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-4.7-Flash-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-4.7-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/GLM-4.7-Flash-GGUF with Ollama:
```
ollama run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL
```

Unsloth Studio new

How to use unsloth/GLM-4.7-Flash-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-4.7-Flash-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-4.7-Flash-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-4.7-Flash-GGUF to start chatting

Pi new

How to use unsloth/GLM-4.7-Flash-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-4.7-Flash-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-4.7-Flash-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/GLM-4.7-Flash-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-4.7-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-4.7-Flash-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/GLM-4.7-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/GLM-4.7-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/GLM-4.7-Flash-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.GLM-4.7-Flash-GGUF-UD-Q4_K_XL

List all available models

lemonade list

New flag: kv-unified. Performance report: 90 t/s on RTX 4090D 48GB

#18

by SlavikF - opened Jan 27

Discussion

SlavikF

Jan 27

•

edited Jan 27

Recently llama.cpp added new flag:

--kv-unified
use single unified KV buffer shared across all sequences

kv-unified didn't affect the speed for me, but saved few GBs of VRAM. Now max context fit into 48GB VRAM.
Actual VRAM usage is ~44GB.

Running UD-Q8_K_XL on my system with RTX 4090D 48GB.

prompt processing: 4000 t/s
token generation: 90 t/s

docker compose:

services:
  llama-router:
    image: ghcr.io/ggml-org/llama.cpp:full-cuda12-b7842
    container_name: router
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]
    ports:
      - "8080:8080"
    volumes:
      - /home/slavik/.cache/llama.cpp/router:/root/.cache/llama.cpp/router
      - ./models.ini:/app/models.ini
    entrypoint: ["./llama-server"]
    command: >
      --models-dir /root/.cache/llama.cpp/router
      --models-max 1
      --models-preset ./models.ini
      --host 0.0.0.0  --port 8080

models.ini

version = 1

[local-GLM4.7-30b]
ctx-size=202752
temp=0.7
top-p=1.0
min-p=0.01
jinja=1
kv-unified=1
fit=off

Mostly, everything works great. But sometimes it getting into the loop with very repeated reasoning...

danielhanchen

Unsloth AI org Jan 27

Oh very nice!

mcfadyeni

Jan 27

•

edited Jan 27

Unified KV is now enabled by default in llama.cpp if the number of slots is auto (-1), and since that's the default for number of slots, Unified KV should also be the default 😊

SlavikF

Jan 27

It was not enabled by default for me

mcfadyeni

Jan 27

Interesting, perhaps there's some condition that affects whether it's enabled by default? Maybe GPU architecture or context size?

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