According to their PR, this should only need the same resources as a 13B model. So 26GB @ f16, 13GB at f8. Edit: I may have misread it, they mention it having the same speed and cost as a 13B model, and I assumed that referred to vram footprint, too, but maybe not...
"Mixtral is a sparse mixture-of-experts network. It is a decoder-only model where the feedforward block picks from a set of 8 distinct groups of parameters. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively.
This technique increases the number of parameters of a model while controlling cost and latency, as the model only uses a fraction of the total set of parameters per token. Concretely, Mixtral has 46.7B total parameters but only uses 12.9B parameters per token. It, therefore, processes input and generates output at the same speed and for the same cost as a 12.9B model."