Instructions to use WaveCut/FLUX.2-klein-9B-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/FLUX.2-klein-9B-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/FLUX.2-klein-9B-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
- Local Apps Settings
- Draw Things
- DiffusionBee
| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "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": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "quantization_config": { | |
| "activation_bits": 4, | |
| "activation_eps": 1e-10, | |
| "activation_kernel_backend": "triton_cuda", | |
| "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, | |
| "modules_dtype_dict": {}, | |
| "modules_to_convert": [], | |
| "modules_to_not_convert": [], | |
| "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": "auto", | |
| "weight_bits": 4, | |
| "weight_pack_dtype": "uint8" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.13.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |