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"
- Xet hash:
- a8a97a57ad4faac53d9e070a4fdf4c0fd9f433afc6d6e213e268bee4d68840fc
- Size of remote file:
- 6.33 GB
- SHA256:
- 6c95118c11efe15b09d63e7b773085440237610585da533902788cdfbe135af5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.