One job, one card, one API
Xiaomi: MiMo-V2.6-Flash on Radeon RX 7900 XTX
The sums below use the “Chatbot for a small team” example: 4,200 jobs a month, 1,500 tokens in, 400 out. 8 people, 25 questions on each of 21 working days. 1,500 tokens in (the question plus a short history) and 400 tokens out. A worked example, not a log from a real team.
Check the figures
Xiaomi: MiMo-V2.6-Flash's weights are larger than Radeon RX 7900 XTX's 24 GB on the whole ladder — Q2_K alone is about 116.5 GB. As a MoE model it can run with its experts offloaded to system RAM, but far slower than a card that fits, and this site will not quote a speed for that setup. Choose a smaller model, or a card (or several) that holds the weights.