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

Llama-4-Maverick-17B-128E-Instruct

Meta
GermanLlama 4 Community

Open language model for chat and text. 2 sizes from 108.6B to 401.6B parameters, partly mixture-of-experts (only a part of the parameters is active per token).

  • Mixture-of-experts: 401.6B parameters in total, of which 17.0B 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
4k256k
How much text the model keeps in view at once. More context needs more memory.
Recommendation
4× H100 80 GB

The model needs about 244.1 GB of memory. Hopper, FP8 support.

Weights
241.0 GB
KV cache
1.6 GB
Speed
~75.0 Tok./s

More suitable configurations

CardQuantityTok./sStatus
A40 48 GB8×27.62-3 weeks delivery time
RTX A6000 48 GB8×30.92-3 weeks delivery time
Quadro RTX 8000 48 GB8×22.82-3 weeks delivery time
L40 48 GB8×33.82-3 weeks delivery time
A100 40 GB8×34.12-3 weeks delivery time
A100 80 GB4×53.42-3 weeks delivery time
H100 80 GB4×75.0only 1 in stock