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

Apertus-v1.5-70B

Swiss AI
Apache 2.0

Open language model for chat and text. 2 sizes from 8.9B to 72B parameters.

  • We could not read the architecture of this model. The memory for the context is estimated.

Settings

Quality
4 bit (Q4_K_M) is the most common choice: good quality with low memory requirements.
Context length: 8k tokens
4k32k
How much text the model keeps in view at once. More context needs more memory.
Recommendation
1× H100 80 GB

The model needs about 47.4 GB of memory. Hopper, FP8 support.

Weights
43.2 GB
KV cache
2.7 GB
Speed
~23.0 Tok./s

More suitable configurations

CardQuantityTok./sStatus
Tesla T4 16 GB4×3.22-3 weeks delivery time
Tesla P100 16 GB4×4.02-3 weeks delivery time
Tesla P40 24 GB4×3.82-3 weeks delivery time
Tesla V100 16 GB4×8.9only 1 in stock
Tesla V100 32 GB2×10.2On order, delivery time approx. 1 week
AMD Instinct MI50 16 GB4×6.8only 2 in stock
AMD Instinct MI50 32 GB2×7.9in stock
AMD Instinct MI60 32 GB2×7.32-3 weeks delivery time
AMD Instinct MI100 32 GB2×8.82-3 weeks delivery time
A30 24 GB4×8.62-3 weeks delivery time
RTX A5000 24 GB4×9.02-3 weeks delivery time
A40 48 GB2×9.92-3 weeks delivery time