Tested at Mistral’s scale is a very different thing to tested at OpenAI’s scale.

The scale of being "tested" clearly convinced Meta (beyond OpenAI's scale) [0] HuggingFace [1], Perplexity [2] and unsuprisingly many others in the AI industry [3] that require more compute than GPUs can deliver.

So labelling it "untested" even at Meta's scale as a customer (which exceeds OpenAI's scale) is quiet nonsensical and frankly an uninformed take.

[0] https://www.cerebras.ai/customer-spotlights/meta

[1] https://www.cerebras.ai/news/hugging-face-partners-with-cere...

[2] https://www.cerebras.ai/press-release/cerebras-powers-perple...

[3] https://www.cerebras.ai/customer-spotlights

Meta didn't offer it. They offered the free llama version on their cloud. Maybe now Zuck will be conincrto buy their chips though