This model was converted to MLX format and quantized Q4, NovaSky-AI/Sky-T1-32B-Preview using mlx-lm version 0.4.0. Refer to the original model card for more details on the model.

Use with mlx . pip install mlx-lm . from mlx_lm import load, generate

model, tokenizer = load("jesusoctavioas/Sky-T1-32B-Preview-MLX-Q4") response = generate(model, tokenizer, prompt="hello", verbose=True)

Original model link https://huggingface.co/NovaSky-AI/Sky-T1-32B-Preview .

Downloads last month
1
Safetensors
Model size
5.12B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for jesusoctavioas/Sky-T1-32B-Preview-MLX-Q4

Base model

Qwen/Qwen2.5-32B
Quantized
(20)
this model