Instructions to use EigenLabs/Qwen3.8-27B-MTP-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use EigenLabs/Qwen3.8-27B-MTP-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.8-27B-MTP-bf16 EigenLabs/Qwen3.8-27B-MTP-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "metadata": { | |
| "total_size": 849398784 | |
| }, | |
| "weight_map": { | |
| "fc.weight": "model.safetensors", | |
| "layers.0.input_layernorm.weight": "model.safetensors", | |
| "layers.0.mlp.down_proj.weight": "model.safetensors", | |
| "layers.0.mlp.gate_proj.weight": "model.safetensors", | |
| "layers.0.mlp.up_proj.weight": "model.safetensors", | |
| "layers.0.post_attention_layernorm.weight": "model.safetensors", | |
| "layers.0.self_attn.k_norm.weight": "model.safetensors", | |
| "layers.0.self_attn.k_proj.weight": "model.safetensors", | |
| "layers.0.self_attn.o_proj.weight": "model.safetensors", | |
| "layers.0.self_attn.q_norm.weight": "model.safetensors", | |
| "layers.0.self_attn.q_proj.weight": "model.safetensors", | |
| "layers.0.self_attn.v_proj.weight": "model.safetensors", | |
| "norm.weight": "model.safetensors", | |
| "pre_fc_norm_embedding.weight": "model.safetensors", | |
| "pre_fc_norm_hidden.weight": "model.safetensors" | |
| } | |
| } | |