GROK-1 Support

[apcameron]

Please consider adding support for GROK-1 https://x.ai/blog/grok-os
https://huggingface.co/xai-org/grok-1

[ummite]

I would really like too

[lafintiger]

+1 on that!

[nicoboss]

While waiting for official support I was able to get grok-1.Q4_K_M.gguf from mradermacher/grok-1-GGUF working. To do so I installed latest text-generation-webui CPU version for Windows, opened cmd_windows.bat and entered pip install git+https://github.com/abetlen/llama-cpp-python.git as llama-cpp added grok-1 support in ggerganov/llama.cpp#6204 as discussed in ggerganov/llama.cpp#6120.

For grok-1.Q4_K_M.gguf 256 GB RAM is easily enough - mradermacher lists 193.3 GB as requirement. I'm really happy with the output of grok-1 so far and am looking forward for the weighted/imatrix quants.

[github-actions]

This issue has been closed due to inactivity for 2 months. If you believe it is still relevant, please leave a comment below. You can tag a developer in your comment.