Text Generation
Transformers
Safetensors
MLX
English
Chinese
glm4_moe
conversational
4-bit precision
Instructions to use brAInwav/GLM-4.5-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use brAInwav/GLM-4.5-mlx-4Bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="brAInwav/GLM-4.5-mlx-4Bit") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("brAInwav/GLM-4.5-mlx-4Bit") model = AutoModelForCausalLM.from_pretrained("brAInwav/GLM-4.5-mlx-4Bit", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - MLX
How to use brAInwav/GLM-4.5-mlx-4Bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("brAInwav/GLM-4.5-mlx-4Bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use brAInwav/GLM-4.5-mlx-4Bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "brAInwav/GLM-4.5-mlx-4Bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "brAInwav/GLM-4.5-mlx-4Bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/brAInwav/GLM-4.5-mlx-4Bit
- SGLang
How to use brAInwav/GLM-4.5-mlx-4Bit 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 "brAInwav/GLM-4.5-mlx-4Bit" \ --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": "brAInwav/GLM-4.5-mlx-4Bit", "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 "brAInwav/GLM-4.5-mlx-4Bit" \ --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": "brAInwav/GLM-4.5-mlx-4Bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Pi
How to use brAInwav/GLM-4.5-mlx-4Bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "brAInwav/GLM-4.5-mlx-4Bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "brAInwav/GLM-4.5-mlx-4Bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use brAInwav/GLM-4.5-mlx-4Bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "brAInwav/GLM-4.5-mlx-4Bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "brAInwav/GLM-4.5-mlx-4Bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "brAInwav/GLM-4.5-mlx-4Bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Docker Model Runner
How to use brAInwav/GLM-4.5-mlx-4Bit with Docker Model Runner:
docker model run hf.co/brAInwav/GLM-4.5-mlx-4Bit
- Hermes Agent
How to use brAInwav/GLM-4.5-mlx-4Bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "brAInwav/GLM-4.5-mlx-4Bit"
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 brAInwav/GLM-4.5-mlx-4Bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use brAInwav/GLM-4.5-mlx-4Bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "brAInwav/GLM-4.5-mlx-4Bit"
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 "brAInwav/GLM-4.5-mlx-4Bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Commit History
-
Upload README.md with huggingface_hub
Verified signature8ebeac5 -
Upload generation_config.json with huggingface_hub
Verified signaturea044cbb -
Upload tokenizer.json with huggingface_hub
Verified signature065f2ce -
Upload special_tokens_map.json with huggingface_hub
Verified signature9766162 -
Upload tokenizer_config.json with huggingface_hub
Verified signaturec41854b -
Upload chat_template.jinja with huggingface_hub
Verified signature87960d7 -
Upload config.json with huggingface_hub
Verified signaturef50686a -
Upload model.safetensors.index.json with huggingface_hub
Verified signature9c9bf84 -
Upload model-00039-of-00039.safetensors with huggingface_hub
Verified signaturef44b260 -
Upload model-00038-of-00039.safetensors with huggingface_hub
Verified signature31ebb23 -
Upload model-00037-of-00039.safetensors with huggingface_hub
Verified signature5e4bddc -
Upload model-00036-of-00039.safetensors with huggingface_hub
Verified signaturefe064a1 -
Upload model-00035-of-00039.safetensors with huggingface_hub
Verified signature82f0412 -
Upload model-00034-of-00039.safetensors with huggingface_hub
Verified signatured21402c -
Upload model-00033-of-00039.safetensors with huggingface_hub
Verified signature1f22ed0 -
Upload model-00032-of-00039.safetensors with huggingface_hub
Verified signaturef16ce75 -
Upload model-00031-of-00039.safetensors with huggingface_hub
Verified signaturef1a9d48 -
Upload model-00030-of-00039.safetensors with huggingface_hub
Verified signaturee738014 -
Upload model-00029-of-00039.safetensors with huggingface_hub
Verified signatureeefa35e -
Upload model-00028-of-00039.safetensors with huggingface_hub
Verified signaturec21bece -
Upload model-00027-of-00039.safetensors with huggingface_hub
Verified signaturea26ec11 -
Upload model-00026-of-00039.safetensors with huggingface_hub
Verified signature06b18cf -
Upload model-00025-of-00039.safetensors with huggingface_hub
Verified signature81f2f5a -
Upload model-00024-of-00039.safetensors with huggingface_hub
Verified signatureee64d08 -
Upload model-00023-of-00039.safetensors with huggingface_hub
Verified signature5d8a7e1 -
Upload model-00022-of-00039.safetensors with huggingface_hub
Verified signatureb2857b1 -
Upload model-00021-of-00039.safetensors with huggingface_hub
Verified signature0fc9536 -
Upload model-00020-of-00039.safetensors with huggingface_hub
Verified signatureff1596c -
Upload model-00019-of-00039.safetensors with huggingface_hub
Verified signatureb3f3a82 -
Upload model-00018-of-00039.safetensors with huggingface_hub
Verified signatureb90104e -
Upload model-00017-of-00039.safetensors with huggingface_hub
Verified signaturea7b48ee -
Upload model-00016-of-00039.safetensors with huggingface_hub
Verified signature9d0a80c -
Upload model-00015-of-00039.safetensors with huggingface_hub
Verified signatured767905 -
Upload model-00014-of-00039.safetensors with huggingface_hub
Verified signatured9d9c55 -
Upload model-00013-of-00039.safetensors with huggingface_hub
Verified signatureaa87a3b -
Upload model-00012-of-00039.safetensors with huggingface_hub
Verified signature2fcca65 -
Upload model-00011-of-00039.safetensors with huggingface_hub
Verified signature6a188c7 -
Upload model-00010-of-00039.safetensors with huggingface_hub
Verified signaturec82bd8d -
Upload model-00009-of-00039.safetensors with huggingface_hub
Verified signature9db18e3 -
Upload model-00008-of-00039.safetensors with huggingface_hub
Verified signature7212c41 -
Upload model-00007-of-00039.safetensors with huggingface_hub
Verified signature909544c -
Upload model-00006-of-00039.safetensors with huggingface_hub
Verified signature35ae812 -
Upload model-00005-of-00039.safetensors with huggingface_hub
Verified signature763f8b5 -
Upload model-00004-of-00039.safetensors with huggingface_hub
Verified signature0c171a0 -
Upload model-00003-of-00039.safetensors with huggingface_hub
Verified signatureb57683e -
Upload model-00002-of-00039.safetensors with huggingface_hub
Verified signaturea61c0e4 -
Upload model-00001-of-00039.safetensors with huggingface_hub
Verified signature9d9071c -
initial commit
Verified signature6664222