Instructions to use pipenetwork/DeepSeek-V4-Flash-MLX-REAP25 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use pipenetwork/DeepSeek-V4-Flash-MLX-REAP25 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/DeepSeek-V4-Flash-MLX-REAP25") 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/DeepSeek-V4-Flash-MLX-REAP25 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/DeepSeek-V4-Flash-MLX-REAP25" --prompt "Once upon a time"
Ctrl+K
- deepseek_v4_mlx
- 1.52 kB
- 7.26 kB
- 2.07 kB
- 170 Bytes
- 5.44 GB xet
- 5.36 GB xet
- 5.03 GB xet
- 5.02 GB xet
- 5.64 GB xet
- 5.02 GB xet
- 5.7 GB xet
- 5 GB xet
- 5.42 GB xet
- 5 GB xet
- 5.03 GB xet
- 5.6 GB xet
- 5.05 GB xet
- 5.06 GB xet
- 5.58 GB xet
- 5.74 GB xet
- 5.25 GB xet
- 5.23 GB xet
- 5.1 GB xet
- 5.69 GB xet
- 5.73 GB xet
- 5 GB xet
- 5.01 GB xet
- 5.69 GB xet
- 1.58 GB xet
- 177 kB
- 6.37 MB
- 801 Bytes