Text Generation
MLX
Safetensors
kimi_k3
Mixture of Experts
reap
pruned
kimi
apple-silicon
custom_code
Instructions to use pipenetwork/Kimi-K3-REAP73-zh-code-MLX-mxfp4-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use pipenetwork/Kimi-K3-REAP73-zh-code-MLX-mxfp4-q8 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("pipenetwork/Kimi-K3-REAP73-zh-code-MLX-mxfp4-q8") 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 pipenetwork/Kimi-K3-REAP73-zh-code-MLX-mxfp4-q8 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "pipenetwork/Kimi-K3-REAP73-zh-code-MLX-mxfp4-q8" --prompt "Once upon a time"
Ctrl+K
- kimi_k3_vl
- 1.52 kB
- 3.07 kB
- 6.51 kB
- 452 kB
- 11.3 kB
- 22.8 kB
- 53 Bytes
- 37.7 kB
- 7.66 kB
- 16.6 kB
- 6.69 kB
- 13.8 kB
- 5.91 GB xet
- 6.33 GB xet
- 5.44 GB xet
- 6.25 GB xet
- 6.33 GB xet
- 6.11 GB xet
- 5.38 GB xet
- 6.53 GB xet
- 6.11 GB xet
- 6.33 GB xet
- 5.38 GB xet
- 6.31 GB xet
- 6.33 GB xet
- 6.33 GB xet
- 5.41 GB xet
- 6.28 GB xet
- 6.33 GB xet
- 6.33 GB xet
- 5.44 GB xet
- 6.25 GB xet
- 6.33 GB xet
- 6.11 GB xet
- 5.38 GB xet
- 6.53 GB xet
- 6.11 GB xet
- 6.33 GB xet
- 5.38 GB xet
- 6.31 GB xet
- 6.33 GB xet
- 6.33 GB xet
- 5.41 GB xet
- 6.28 GB xet
- 6.33 GB xet
- 6.33 GB xet
- 5.44 GB xet
- 6.25 GB xet
- 6.33 GB xet