Instructions to use Akicou/GLM-4.7-Flash-REAP-50-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Akicou/GLM-4.7-Flash-REAP-50-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Akicou/GLM-4.7-Flash-REAP-50-GGUF",
	filename="GLM-4.7-Flash-REAP-50.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Akicou/GLM-4.7-Flash-REAP-50-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M

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 Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M

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 Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Akicou/GLM-4.7-Flash-REAP-50-GGUF with Ollama:
```
ollama run hf.co/Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Akicou/GLM-4.7-Flash-REAP-50-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 Akicou/GLM-4.7-Flash-REAP-50-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 Akicou/GLM-4.7-Flash-REAP-50-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Akicou/GLM-4.7-Flash-REAP-50-GGUF to start chatting

Docker Model Runner
How to use Akicou/GLM-4.7-Flash-REAP-50-GGUF with Docker Model Runner:
```
docker model run hf.co/Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M
```

Lemonade

How to use Akicou/GLM-4.7-Flash-REAP-50-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Akicou/GLM-4.7-Flash-REAP-50-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GLM-4.7-Flash-REAP-50-GGUF-Q4_K_M

List all available models

lemonade list

GLM-4.7-Flash-REAP-50-GGUF

This model was converted to GGUF format from Akicou/GLM-4.7-Flash-REAP-50 using GGUF Forge.

Quants

The following quants are available: Q3_K_S, Q2_K, Q3_K_M, Q3_K_L, Q4_0, Q4_K_S, Q4_K_M, Q5_0, Q5_K_S, Q5_K_M, Q6_K, Q8_0

Conversion Stats

Metric	Value
Job ID	`e4b8171e-c612-47d3-8a45-cb1c14eb9636`
GGUF Forge Version	v5.5
Total Time	32.3min
Avg Time per Quant	3.0min

Step Breakdown

Download: 4.1min
FP16 Conversion: 2.5min
Quantization: 25.6min

🚀 Convert Your Own Models

Want to convert more models to GGUF?

👉 gguforge.com — Free hosted GGUF conversion service. Login with HuggingFace and request conversions instantly!

Model tree for Akicou/GLM-4.7-Flash-REAP-50-GGUF

Base model

zai-org/GLM-4.7-Flash

Finetuned

Akicou/GLM-4.7-Flash-REAP-50

Quantized

(4)

this model