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

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

NVIDIA
GermanOpenMDW 1.1

Open language model for chat and text. 31.6B Parameter, partly mixture-of-experts (only a part of the parameters is active per token).

  • Mixture-of-experts: 31.6B parameters in total, of which 3.0B 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
1× H100 80 GB

The model needs about 20.9 GB of memory. Hopper, FP8 support.

Weights
19.0 GB
KV cache
0.4 GB
Speed
~506.9 Tok./s

More suitable configurations

CardQuantityTok./sStatus
Tesla T4 16 GB2×81.22-3 weeks delivery time
Tesla P100 16 GB2×102.32-3 weeks delivery time
Tesla P40 24 GB1×103.62-3 weeks delivery time
Tesla V100 16 GB2×226.2only 1 in stock
Tesla V100 32 GB1×244.3On order, delivery time approx. 1 week
AMD Instinct MI50 16 GB2×173.4in stock
AMD Instinct MI50 32 GB1×187.3in stock
AMD Instinct MI60 32 GB1×172.92-3 weeks delivery time
AMD Instinct MI100 32 GB1×209.12-3 weeks delivery time
A30 24 GB1×236.42-3 weeks delivery time
RTX A5000 24 GB1×246.32-3 weeks delivery time
A40 48 GB1×234.92-3 weeks delivery time