• 3 % discount on prepayment
  • Insured shipping from Switzerland
  • Sustainable: refurbished instead of new
  • Warranty on all cards
← Back to overview

Kimi-K2.6

Moonshot AI
MIT

Open language model for chat and text. 3 sizes from 49.1B to 2.8T parameters, partly mixture-of-experts (only a part of the parameters is active per token).

  • Mixture-of-experts: 1'026.9B parameters in total, of which 33.3B active per token. Memory requirement depends on all parameters, speed on the active ones.

Settings

Quality
4 bit (Q4_K_M) is the most common choice: good quality with low memory requirements.
Context length: 8k tokens
4k256k
How much text the model keeps in view at once. More context needs more memory.
Too large

Our current cards are not enough for this combination. Choose a more compact variant or contact us for advice.