How to use mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit 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-ai-DeepSeek-V4-Flash-4bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True)
How to use mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit" --prompt "Once upon a time"
Could you make a 4 bit dwq quant of this model?
i will try
· Sign up or log in to comment
