Image-Text-to-Text
MLX
Safetensors
English
Chinese
glm4v
reasoning
thinking
vision-language
multimodal
conversational
8-bit precision
Instructions to use mlx-community/GLM-4.1V-9B-Thinking-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/GLM-4.1V-9B-Thinking-8bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mlx-community/GLM-4.1V-9B-Thinking-8bit") config = load_config("mlx-community/GLM-4.1V-9B-Thinking-8bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Add MLX 8-bit conversion of GLM-4.1V-9B-Thinking with vision preserved and weight-level fidelity vs bf16
9677807 verified | { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": false, | |
| "do_lower_case": false, | |
| "eos_token": "<|endoftext|>", | |
| "extra_special_tokens": [ | |
| "<|endoftext|>", | |
| "[MASK]", | |
| "[gMASK]", | |
| "[sMASK]", | |
| "<sop>", | |
| "<eop>", | |
| "<|system|>", | |
| "<|user|>", | |
| "<|assistant|>", | |
| "<|observation|>", | |
| "<|begin_of_image|>", | |
| "<|end_of_image|>", | |
| "<|begin_of_video|>", | |
| "<|end_of_video|>", | |
| "<|image|>", | |
| "<|video|>" | |
| ], | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 65536, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "left", | |
| "processor_class": "Glm46VProcessor", | |
| "remove_space": false, | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |