Falcon-H1 1.5B MLX BF16

MLX port of tiiuae/Falcon-H1-1.5B-Base for Apple Silicon.

For 4-bit: sdkv2/falcon-h1-1.5b-mlx-4bit

Usage

from mlx_lm import load, generate

model, tokenizer = load("sdkv2/falcon-h1-1.5b-mlx-bf16")
response = generate(model, tokenizer, prompt="Hello", verbose=True)

Downloads last month: 429

Safetensors

Model size

2B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized