Instructions to use inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX 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("inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX") 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 inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX" --prompt "Once upon a time"
- Atomic Chat
- Xet hash:
- 5316d70dd5c2c640fcf46651808cb2503c7cd13ebee79f39f5a2e848fb1452c6
- Size of remote file:
- 13 GB
- SHA256:
- b85975ff649e50af534b48e90ea81514d9b1446fb72a1e42be00dd2c013a6666
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.