Instructions to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM",
	filename="glm-4.7-flash-Opus-Reasoning-Q4_KM.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM 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 austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM
# Run inference directly in the terminal:
llama cli -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM
# Run inference directly in the terminal:
llama cli -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

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 austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM
# Run inference directly in the terminal:
./llama-cli -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

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 austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM
# Run inference directly in the terminal:
./build/bin/llama-cli -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

Use Docker

docker model run hf.co/austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

LM Studio
Jan

vLLM

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

Ollama
How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with Ollama:
```
ollama run hf.co/austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM
```

Unsloth Studio

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM 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 austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM 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 austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM to start chatting

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

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": "austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

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 austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

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 "austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM" \
  --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"

Docker Model Runner
How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with Docker Model Runner:
```
docker model run hf.co/austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM
```

Lemonade

How to use austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

Run and chat with the model

lemonade run user.glm-4.7-flash-Opus-Reasoning-Q4_KM-{{QUANT_TAG}}

List all available models

lemonade list

GLM-4.7-Flash Opus Reasoning (GGUF Q4_K_M)

Production-ready quantized model - 16.9 GB (69.7% compressed)

Model Description

This is a GGUF Q4_K_M quantized version of the fine-tuned GLM-4.7-Flash model, optimized for fast inference with llama.cpp.

Quantization Details

Format: GGUF (GPT-Generated Unified Format)
Quantization: Q4_K_M (4-bit K-means)
Model Size: 16.9 GB (from 55.8 GB)
Compression: 69.7% size reduction
Precision: 4.84 BPW (bits per weight)

Usage with llama.cpp

Command Line

# Download llama.cpp and build
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
cmake -B build
cmake --build build --config Release -j

# Run inference
./build/bin/llama-cli   -m glm-flash-2500-Q4_KM.gguf   -p "Write a Python function to merge two sorted lists"   -n 256   -t 8

Python Binding

from llama_cpp import Llama

model = Llama(
    model_path="glm-flash-2500-Q4_KM.gguf",
    n_ctx=8192,
    n_threads=8,
)

output = model(
    "Write a function to merge two sorted lists:",
    max_tokens=256,
    stop=["

"],
    echo=True
)
print(output['choices'][0]['text'])

Interactive Mode

./build/bin/llama-cli   -m glm-flash-2500-Q4_KM.gguf   -cnv   -i   -t 8

Performance Metrics

Prompt Speed: ~65 tokens/second
Generation Speed: ~22 tokens/second
Memory Usage: Efficient for production
Latency: Low latency inference

Model Capabilities

This model excels at:

Tool-use: Agent workflows and function calling
Reasoning: Mathematical and logical problems
Coding: Python, debugging, code explanation
Problem Solving: Multi-step reasoning

Hardware Requirements

Minimum:

RAM: 20 GB
CPU: Modern multi-core processor
Storage: 20 GB free space

Recommended:

RAM: 32 GB
CPU: 8+ cores
GPU: Not required (CPU inference)

Base Model

This GGUF model was created from: https://huggingface.co/austindixson/glm-4.7-flash-Opus-Reasoning

Which was fine-tuned from: https://huggingface.co/unsloth/GLM-4.7-Flash

License

Apache 2.0

Quantized and optimized for production use

Downloads last month: 44

GGUF

Model size

30B params

Architecture

deepseek2

Hardware compatibility

Model tree for austindixson/glm-4.7-flash-Opus-Reasoning-Q4_KM

Base model

zai-org/GLM-4.7-Flash

Finetuned

unsloth/GLM-4.7-Flash

Finetuned

austindixson/glm-4.7-flash-Opus-Reasoning

Quantized

(1)

this model