Text-to-Image
MLX
English
Chinese
image-generation
image-editing
quantized
4-bit precision
apple-silicon
minimax-h3-image
Instructions to use zimageapp/MiniMax-H3-Image-MLX-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use zimageapp/MiniMax-H3-Image-MLX-Q4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download zimageapp/MiniMax-H3-Image-MLX-Q4 --local-dir MiniMax-H3-Image-MLX-Q4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download q4_components.json from zimageapp/MiniMax-H3-Image-MLX-Q4: direct link, hf CLI and curl.
- Browser
- Download file 2.89 kB
-
https://huggingface.co/zimageapp/MiniMax-H3-Image-MLX-Q4/resolve/main/q4_components.json
- Command line
-
hf download hf://zimageapp/MiniMax-H3-Image-MLX-Q4/q4_components.json
-
curl -L -o q4_components.json https://huggingface.co/zimageapp/MiniMax-H3-Image-MLX-Q4/resolve/main/q4_components.json
2.89 kB
| { | |
| "format_version": 1, | |
| "repository": "zimageapp/MiniMax-H3-Image-MLX-Q4", | |
| "base_model": "MiniMaxAI/MiniMax-H3-Image", | |
| "pipeline": "text-to-image and image editing", | |
| "quantization": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "mode": "affine", | |
| "packing": "uint32, eight low-nibble-first values per word", | |
| "dequantization": "weight = q * scale + bias", | |
| "scale_dtype": "bfloat16", | |
| "unquantized_tensors": "Mixed original BF16/FP32; Image VAE FP16" | |
| }, | |
| "compatibility": { | |
| "tensor_layout": "Native H3/Locraft naming; MLX-compatible affine packed matrices", | |
| "validated_runtime": "Locraft C++/Metal native H3 Image", | |
| "mlx_end_to_end": "Not implemented/validated; not a drop-in mlx-lm or Diffusers checkpoint" | |
| }, | |
| "sampling": { | |
| "evaluations": 6, | |
| "sigmas": [ | |
| 1.0, | |
| 0.9675236940383911, | |
| 0.8875485062599182, | |
| 0.75, | |
| 0.5327739119529724, | |
| 0.23200887441635132, | |
| 0.0 | |
| ], | |
| "guidance_scale": 1, | |
| "loras": [] | |
| }, | |
| "components": [ | |
| { | |
| "path": "diffusion_models/minimax_h3_image_int4.safetensors", | |
| "bytes": 11390105242, | |
| "sha256": "ec8e688a5918c0783b632ac50a4ac8d0ebf128d53fc29a46eb356898f8fb7c90", | |
| "tensor_count": 996, | |
| "source_url": "https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/0bb149f51e3156ed4b90dd45d5620346bfe1df8f/diffusion_models/minimax_h3_image_pruned_bf16.safetensors", | |
| "source_sha256": "a767f5325db019588b3491a93d80288d336c826a7aeb87bec67675e554367222", | |
| "modifications": "209 matrices quantized to affine Q4/group64; FP32 time/projection/output-head islands retained." | |
| }, | |
| { | |
| "path": "text_encoders/qwen3vl_32b_minimax_h3_int4.safetensors", | |
| "bytes": 16466386400, | |
| "sha256": "acb9a9dbbc8977250fe8e6aa25eb69a8294f1015332b0c6182deb31c3a9c7cd8", | |
| "tensor_count": 1602, | |
| "source_repository": "Comfy-Org/MiniMax-H3", | |
| "source_family": "MiniMaxAI/MiniMax-H3", | |
| "source_layout": "Locally quantized and merged H3 Qwen3-VL32B encoder, with embedded configuration/tokenizer.", | |
| "modifications": "Affine Q4/group64, merged native layout, embedded tokenizer. Publication copy removes 864 bytes of inter-tensor padding; all 1602 tensor payloads and metadata verified unchanged.", | |
| "original_aligned_file_sha256": "9a059b9dc83307f3caed3af31f4a33c78b4147194bdc3dc5adeb797caea1a25d", | |
| "original_aligned_file_bytes": 16466387264 | |
| }, | |
| { | |
| "path": "vae/minimax_h3_image_vae_fp16.safetensors", | |
| "bytes": 1168505312, | |
| "sha256": "d80e9c2e5cfc9844869961ff5a58c9a9e52182df6bfb30b26018dd7f348721af", | |
| "tensor_count": 416, | |
| "source_url": "https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/0bb149f51e3156ed4b90dd45d5620346bfe1df8f/vae/minimax_h3_image_vae_fp16.safetensors", | |
| "modifications": "None; original FP16 Image VAE." | |
| } | |
| ], | |
| "total_weight_bytes": 29024996954 | |
| } | |