Instructions to use Ex0bit/GLM-4.7-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/GLM-4.7-PRISM with Transformers:

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

pipe = pipeline("text-generation", model="Ex0bit/GLM-4.7-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ex0bit/GLM-4.7-PRISM")
model = AutoModelForCausalLM.from_pretrained("Ex0bit/GLM-4.7-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Ex0bit/GLM-4.7-PRISM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ex0bit/GLM-4.7-PRISM",
	filename="GLM-4.7-PRISM-IQ1_S.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 Ex0bit/GLM-4.7-PRISM with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/GLM-4.7-PRISM:IQ1_S
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/GLM-4.7-PRISM:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/GLM-4.7-PRISM:IQ1_S
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/GLM-4.7-PRISM:IQ1_S

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 Ex0bit/GLM-4.7-PRISM:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/GLM-4.7-PRISM:IQ1_S

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 Ex0bit/GLM-4.7-PRISM:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/GLM-4.7-PRISM:IQ1_S

Use Docker

docker model run hf.co/Ex0bit/GLM-4.7-PRISM:IQ1_S

LM Studio
Jan

vLLM

How to use Ex0bit/GLM-4.7-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/GLM-4.7-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/GLM-4.7-PRISM:IQ1_S

SGLang

How to use Ex0bit/GLM-4.7-PRISM 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 "Ex0bit/GLM-4.7-PRISM" \
    --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": "Ex0bit/GLM-4.7-PRISM",
		"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 "Ex0bit/GLM-4.7-PRISM" \
        --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": "Ex0bit/GLM-4.7-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ex0bit/GLM-4.7-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/GLM-4.7-PRISM:IQ1_S
```

Unsloth Studio

How to use Ex0bit/GLM-4.7-PRISM 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 Ex0bit/GLM-4.7-PRISM 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 Ex0bit/GLM-4.7-PRISM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/GLM-4.7-PRISM to start chatting

How to use Ex0bit/GLM-4.7-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/GLM-4.7-PRISM:IQ1_S

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": "Ex0bit/GLM-4.7-PRISM:IQ1_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ex0bit/GLM-4.7-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/GLM-4.7-PRISM:IQ1_S

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 Ex0bit/GLM-4.7-PRISM:IQ1_S

Run Hermes

hermes

Docker Model Runner
How to use Ex0bit/GLM-4.7-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/GLM-4.7-PRISM:IQ1_S
```

Lemonade

How to use Ex0bit/GLM-4.7-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/GLM-4.7-PRISM:IQ1_S

Run and chat with the model

lemonade run user.GLM-4.7-PRISM-IQ1_S

List all available models

lemonade list

Hi, could you perform the same PRISM on the Minimax M2.1?

by win10 - opened Dec 28, 2025

Discussion

win10

Dec 28, 2025

Hi, could you perform the same PRISM on the Minimax M2.1?

clevnumb

Dec 29, 2025

Yes please!

Ex0bit

Owner Dec 29, 2025

•

edited Dec 29, 2025

MiniMax-M2.1 is an incredible agentic model for sure. And a MiniMax-M2.1-PRISM would be amazing.

I've been donating the SOTA PRISM models out of pocket—unfortunately the compute, storage, and hosting costs are very expensive, and We've burned through available budget. If enough of us want it, we can prioritize MiniMax-M2.1-PRISM as the next community release.

GLM-4.7-PRISM just crossed 2,000+ downloads—if even a small fraction of us sponsored to help cover hard-costs, we'd make it happen.

https://ko-fi.com/ericelbaz

Ex0bit

Owner Jan 1

@clevnumb , @win10 MiniMax-M2.1-PRISM is out and available here: https://huggingface.co/Ex0bit/MiniMax-M2.1-PRISM, please consider supporting the work!

Ex0bit changed discussion status to closed Jan 2

clevnumb

Jan 2

@clevnumb , @win10 MiniMax-M2.1-PRISM is out and available here: https://huggingface.co/Ex0bit/MiniMax-M2.1-PRISM, please consider supporting the work!

First attempt using this and it just loops on thinking, with "Oh wait, I need to.....", etc.....had to cancel it. :-(

I will try more later...

Ex0bit

Owner Jan 2

•

edited Jan 2

Good timing @clevnumb ! We found and fixed a target layer selection bug in the initial IQ1_S quant that was likely causing your issue —re-upload in progress, along with higher BPW quants IQ2_M, IQ4_NL (apologies, but you'll need to re-download the fixed quant).

Note: low-BPW quants can sometimes cause looping; raising the repeat penalty or using a higher BPW quant should help. The full BF16 testing was beautiful to see in action!

clevnumb

Jan 3

Good timing @clevnumb ! We found and fixed a target layer selection bug in the initial IQ1_S quant that was likely causing your issue —re-upload in progress, along with higher BPW quants IQ2_M, IQ4_NL (apologies, but you'll need to re-download the fixed quant).

Note: low-BPW quants can sometimes cause looping; raising the repeat penalty or using a higher BPW quant should help. The full BF16 testing was beautiful to see in action!

I wish I could try those larger quants but on my unified memory Strix Halo system that has 96GB, total, using CachyOS, I can only afford 90GB of VRAM to these models... (only, lol). I'll try the fixed one, thank you!

clevnumb

Jan 3

Sorry, I meant with the GLM 4.7, I got the loop by the way...

Ex0bit

Owner Jan 3

•

edited Jan 3

Thanks for testing @clevnumb .GLM4.7-PRISM got an even weight abliteration, it’s massive original size didn’t allow for per-weight SNR. we’ll take a more fine tuned stab at updating the model with per weight abliteration once funding allows or when GLM-4.7-Flash comes out. For now higher repeat penalty should help.

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