Feature Extraction
Transformers
Safetensors
kimi_k3
compressed-tensors
LLM Compressor
vLLM
custom_code
8-bit precision
Instructions to use RedHatAI/Kimi-K3-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/Kimi-K3-NVFP4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="RedHatAI/Kimi-K3-NVFP4", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RedHatAI/Kimi-K3-NVFP4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- 1.58 kB
- 1.16 kB
- 200 Bytes
- 111 kB
- 11.3 kB
- 22.8 kB
- 7.66 kB
- 6.69 kB
- 13.8 kB
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 19.9 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 19.9 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet
- 20 GB xet