Qwen2.5 Math 72B Instruct 6-bit MLX

MLX version of Qwen2.5 Math 72B Instruct

This model was converted to MLX format from https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct using mlx-lm version 0.22.5.

Model Details

For more details, please refer to blog post and GitHub repo.

Use with mlx

pip install -U mlx-lm
python -m mlx_lm.generate --model TheCluster/Qwen2.5-Math-72B-Instruct-mlx-6bit --max-tokens 1024 --temperature 0.5 --prompt "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
Downloads last month
2
Safetensors
Model size
15.9B params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TheCluster/Qwen2.5-Math-72B-Instruct-mlx-6bit

Base model

Qwen/Qwen2.5-72B
Quantized
(12)
this model

Collection including TheCluster/Qwen2.5-Math-72B-Instruct-mlx-6bit