Image-Text-to-Video
Diffusers
Safetensors
orbitquant
comfyui
w4
w4a4
native-w4a4-transformer-runtime
text-to-video
audio-video-generation
8-bit precision
Instructions to use WaveCut/MiniMax-H3-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/MiniMax-H3-OrbitQuant-W4A4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/MiniMax-H3-OrbitQuant-W4A4", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_id": 151655, | |
| "model_type": "qwen3_vl", | |
| "quantization_config": { | |
| "activation_bits": 4, | |
| "activation_eps": 1e-10, | |
| "activation_kernel_backend": "auto", | |
| "activation_norm_dtype": "float32", | |
| "adaln_group_size": 64, | |
| "adaln_policy": "int4_rtn", | |
| "artifact_format_version": 1, | |
| "block_size": "paper", | |
| "codebook": "lloyd_max", | |
| "codebook_dtype": "float32", | |
| "codebook_version": 2, | |
| "lowbit_boundary_protection": "auto", | |
| "lowbit_interior_protection": "auto", | |
| "lowbit_protected_bits": 4, | |
| "lowbit_protected_blocks": 4, | |
| "modules_dtype_dict": {}, | |
| "modules_to_convert": [], | |
| "modules_to_not_convert": [ | |
| "model.visual", | |
| "model.language_model.embed_tokens", | |
| "model.language_model.norm", | |
| "lm_head" | |
| ], | |
| "modules_to_use_adaln": [], | |
| "packed_matmul_block_k": 128, | |
| "packed_matmul_block_m": 64, | |
| "packed_matmul_block_n": 64, | |
| "packed_matmul_num_warps": 4, | |
| "quant_method": "orbitquant", | |
| "rotation": "rpbh", | |
| "rotation_seed": 0, | |
| "row_norm_dtype": "bfloat16", | |
| "runtime_mode": "auto_fused", | |
| "target_policy": "universal", | |
| "w4a4_int8_weight_cache": false, | |
| "weight_bits": 4, | |
| "weight_pack_dtype": "uint8", | |
| "weight_row_tile_size": 256 | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 25600, | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_vl_text", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_theta": 5000000, | |
| "rope_type": "default" | |
| }, | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.14.1", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "depth": 27, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_vl_vision", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 5120, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652 | |
| } | |