from mlx_lm import load, generate

model, tokenizer = load("salohcin714/granite-4.1-8b-8bit-gptq-mlx")
messages = [{"role": "user", "content": "Hello"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Modifications

Weights converted to MLX safetensors layout and quantized (8-bit affine quantization, group size 64, via GPTQ Hessian-based calibration). Redundant tied lm_head.weight dropped where the model ties input/output embeddings. No fine-tuning; no added training data.

License and attribution

Licensed under Apache 2.0. Original weights by the Granite Team, IBM. See the upstream model card and the included LICENSE file for the full text.

Disclaimer

This repository is not affiliated with or endorsed by IBM. "Granite" is an IBM trademark, used here descriptively to identify the origin of the base model. IBM's published benchmarks describe the original weights, not this quantized/converted artifact, and must not be read as claims about this repo.