Instructions to use MrMofer/MiniMax-H3-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use MrMofer/MiniMax-H3-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiniMax-H3-MLX-8bit MrMofer/MiniMax-H3-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| {"hidden_size": 5376, "num_layers": 50, "token_refiner_num_layers": 2, "num_attention_heads": 56, "attention_head_dim": 128, "ffn_hidden_size": 14336, "latents_dim": 24, "audio_latents_dim": 32, "patch_size": [1, 2, 2], "text_dim": 5120, "timestep_input_dim": 256, "time_embed_hidden_size": 5376, "time_embed_dim": 2688, "adaln_out_features": 96768, "final_adaln_out_features": 10752, "rope_inv_freq_len": 16, "rope_theta": 10000.0, "norm_eps": 1e-5, "qk_norm_eps": 1e-5, "final_norm_eps": 1e-5} | |