Instructions to use mlx-community/DeepSeek-V4-Flash-3bit-DQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/DeepSeek-V4-Flash-3bit-DQ 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/DeepSeek-V4-Flash-3bit-DQ") 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/DeepSeek-V4-Flash-3bit-DQ 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/DeepSeek-V4-Flash-3bit-DQ" --prompt "Once upon a time"
Ctrl+K
- 1.52 kB
- 123 Bytes
- 39.9 kB
- 170 Bytes
- 4.59 GB xet
- 5.02 GB xet
- 4.86 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.85 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.86 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.85 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.86 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.85 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.86 GB xet
- 5.01 GB xet
- 5.01 GB xet
- 4.85 GB xet
- 5.01 GB xet
- 4.89 GB xet
- 563 MB xet
- 228 kB
- 10.1 MB
- 368 Bytes