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

Devstral-2-123B-Instruct-2512

Mistral AI
Apache 2.0

Open model for programmers. 2 sizes from 24B to 125B parameters.

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.
Recommendation
4× Tesla V100 32 GB

The model needs about 79.5 GB of memory. Passively cooled, fan and 8-pin EPS cable required.

Weights
75.0 GB
KV cache
3.0 GB
Speed
~5.2 Tok./s

More suitable configurations

CardQuantityTok./sStatus
Tesla T4 16 GB8×1.52-3 weeks delivery time
Tesla P100 16 GB8×1.92-3 weeks delivery time
Tesla P40 24 GB4×2.22-3 weeks delivery time
Tesla V100 16 GB8×4.1only 1 in stock
Tesla V100 32 GB4×5.2On order, delivery time approx. 1 week
AMD Instinct MI50 16 GB8×3.2only 2 in stock
AMD Instinct MI50 32 GB4×4.0only 2 in stock
AMD Instinct MI60 32 GB4×3.72-3 weeks delivery time
AMD Instinct MI100 32 GB4×4.52-3 weeks delivery time
A30 24 GB4×5.02-3 weeks delivery time
RTX A5000 24 GB4×5.22-3 weeks delivery time
A40 48 GB2×5.72-3 weeks delivery time