How to use Aryagm/HRM-Text-1B-MLX-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("Aryagm/HRM-Text-1B-MLX-4bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True)
How to use Aryagm/HRM-Text-1B-MLX-4bit with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "Aryagm/HRM-Text-1B-MLX-4bit" --prompt "Once upon a time"
can you try adding benchmarks to see that whether should I go with this quantized model or the one with original precision
· Sign up or log in to comment
