Image-Text-to-Text
MLX
Safetensors
English
molmo_point
multimodal
olmo
molmo
molmo2
conversational
custom_code
4-bit precision
Instructions to use mlx-community/MolmoPoint-8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MolmoPoint-8B-4bit 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/MolmoPoint-8B-4bit") config = load_config("mlx-community/MolmoPoint-8B-4bit") # 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
| { | |
| "adapter_config": { | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "sdpa", | |
| "float32_attention": true, | |
| "head_dim": 72, | |
| "hidden_act": "silu", | |
| "hidden_size": 1152, | |
| "image_feature_dropout": 0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "model_type": "molmo_point", | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 16, | |
| "pooling_attention_mask": true, | |
| "positional_embeddings": null, | |
| "residual_dropout": 0.0, | |
| "text_hidden_size": 4096, | |
| "vit_layers": [ | |
| -3, | |
| -9 | |
| ] | |
| }, | |
| "architectures": [ | |
| "MolmoPointForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_molmo_point.MolmoPointConfig", | |
| "AutoModelForImageTextToText": "modeling_molmo_point.MolmoPointForConditionalGeneration" | |
| }, | |
| "dtype": "float32", | |
| "embed_location": false, | |
| "embed_selected_vit_patch": "linear", | |
| "eos_token_id": 151645, | |
| "frame_end_token_id": 151944, | |
| "frame_start_token_id": 151943, | |
| "image_col_id": 151939, | |
| "image_end_token_id": 151937, | |
| "image_high_res_id": 151938, | |
| "image_non_indexable_patch_id": 151942, | |
| "image_patch_id": 151938, | |
| "image_start_token_id": 151936, | |
| "initializer_range": 0.02, | |
| "layer_norm_x": true, | |
| "location_token_id": 151949, | |
| "low_res_image_start_token_id": null, | |
| "mask_patches": "always", | |
| "mask_repeats": "inference", | |
| "mask_subpatches": "inference", | |
| "model_type": "molmo_point", | |
| "no_more_points_class": true, | |
| "norm_logits": true, | |
| "patch_embed_dim": 512, | |
| "patch_embedding_kind": "image_feature0", | |
| "patch_location": "3x3", | |
| "patch_token_id": 151947, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "subpatch_token_id": 151948, | |
| "text_config": { | |
| "additional_vocab_size": 128, | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "sdpa", | |
| "embedding_dropout": 0.0, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "layer_norm_eps": 1e-06, | |
| "max_position_embeddings": 37376, | |
| "model_type": "molmo2_text", | |
| "norm_after": false, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "qk_norm_type": "qwen3", | |
| "qkv_bias": false, | |
| "residual_dropout": 0.0, | |
| "rope_scaling": null, | |
| "rope_scaling_layers": null, | |
| "rope_theta": 1000000.0, | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": false, | |
| "token_prediction_rotary": "one_d", | |
| "token_prediction_rotary_theta": 50000.0, | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "use_frame_special_tokens": true, | |
| "vision_config": {}, | |
| "vit_config": { | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "sdpa", | |
| "float32_attention": true, | |
| "head_dim": 72, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_default_input_size": [ | |
| 378, | |
| 378 | |
| ], | |
| "image_num_pos": 729, | |
| "image_patch_size": 14, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "molmo2", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_key_value_heads": 16, | |
| "residual_dropout": 0.0 | |
| } | |
| } |