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

MiniMax-M2.7

MiniMax
Eigene Lizenz

Open language model for chat and text. 2 sizes from 228.7B to 427B parameters, partly mixture-of-experts (only a part of the parameters is active per token).

  • Mixture-of-experts: 228.7B parameters in total, of which 11.0B 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
4k128k
How much text the model keeps in view at once. More context needs more memory.
Recommendation
2× H100 80 GB

The model needs about 140.8 GB of memory. Hopper, FP8 support.

Weights
137.2 GB
KV cache
2.1 GB
Speed
~124.0 Tok./s

More suitable configurations

CardQuantityTok./sStatus
Tesla P40 24 GB8×17.52-3 weeks delivery time
Tesla V100 32 GB8×41.4only 6 in stock
AMD Instinct MI50 32 GB8×31.7only 2 in stock
AMD Instinct MI60 32 GB8×29.32-3 weeks delivery time
AMD Instinct MI100 32 GB8×35.42-3 weeks delivery time
A30 24 GB8×40.02-3 weeks delivery time
RTX A5000 24 GB8×41.72-3 weeks delivery time
A40 48 GB4×50.02-3 weeks delivery time
RTX A6000 48 GB4×55.92-3 weeks delivery time
Quadro RTX 8000 48 GB4×41.42-3 weeks delivery time
L40 48 GB4×61.32-3 weeks delivery time
A100 40 GB4×61.92-3 weeks delivery time