Text Generation
MLX
Safetensors
kimi_k3
kimi-k3
Mixture of Experts
reap
pruned
apple-silicon
code
custom_code
Instructions to use mlx-community/Kimi-K3-mlx-reap160-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Kimi-K3-mlx-reap160-2bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/Kimi-K3-mlx-reap160-2bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/Kimi-K3-mlx-reap160-2bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/Kimi-K3-mlx-reap160-2bit" --prompt "Once upon a time"
- Atomic Chat
Ctrl+K
- kimi_k3_vl
- 1.52 kB
- 3.07 kB
- 4.77 kB
- 355 kB
- 11.3 kB
- 22.8 kB
- 53 Bytes
- 37.7 kB
- 7.66 kB
- 16.6 kB
- 6.69 kB
- 13.8 kB
- 5.69 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.44 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.44 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.41 GB xet
- 5.38 GB xet
- 5.68 GB xet
- 5.44 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.44 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.41 GB xet
- 5.38 GB xet
- 5.68 GB xet
- 5.44 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.76 GB xet
- 5.44 GB xet
- 5.37 GB xet
- 846 MB xet
- 559 kB
- 1.01 kB
- 137 kB
- 2.8 MB xet