# RuntimeError: CUDNN\_STATUS\_ARCH\_MISMATCH

**URL:** <https://discuss.pytorch.org/t/runtimeerror-cudnn-status-arch-mismatch/3580>\
**Category:** vision\
**Created:** [May 31, 2017, 11:22am UTC](https://discuss.pytorch.org/t/runtimeerror-cudnn-status-arch-mismatch/3580 "2017-05-31T11:22:23Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Albert](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/48db29/32.png) [@Albert](https://discuss.pytorch.org/u/Albert)\
**Post date:** [May 31, 2017, 11:22am UTC](https://discuss.pytorch.org/t/runtimeerror-cudnn-status-arch-mismatch/3580/1 "2017-05-31T11:22:23Z")

</div>

Error when I run [main.py](http://main.py) in **MNIST Convnets**.

```auto
root@albert-PC:/media/ww/examples-master/mnist# python main.py 
Traceback (most recent call last):
  File "main.py", line 113, in <module>
    train(epoch)
  File "main.py", line 83, in train
    output = model(data)
  File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 206, in __call__
    result = self.forward(*input, **kwargs)
  File "main.py", line 62, in forward
    x = F.relu(F.max_pool2d(self.conv1(x), 2))
  File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 206, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/conv.py", line 237, in forward
    self.padding, self.dilation, self.groups)
  File "/usr/local/lib/python2.7/dist-packages/torch/nn/functional.py", line 40, in conv2d
    return f(input, weight, bias)
RuntimeError: CUDNN_STATUS_ARCH_MISMATCH

```

GPU: GeForce 710M  
CUDA: 8.0

---

<div class="post-metadata">

**Author:** ![smth](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/smth/32/13_2.png) [@smth](https://discuss.pytorch.org/u/smth)\
**Post date:** [May 31, 2017, 1:56pm UTC](https://discuss.pytorch.org/t/runtimeerror-cudnn-status-arch-mismatch/3580/2 "2017-05-31T13:56:39Z")

</div>

cudnn does not support CUDA arch 2.1 cards. The minimum supported CUDA arch is 3.0

You can find out what CUDA arch your GPU belongs to in this page:

> **[CUDA GPUs](https://developer.nvidia.com/cuda-gpus)**
>
> Recommended GPU for Developers NVIDIA TITAN RTX NVIDIA TITAN RTX is built for data science, AI research, content creation and general GPU development. Built on the Turing architecture, it features 4608, 576 full-speed mixed precision Tensor Cores for...