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

Llama-3.1-8B-Instruct

Meta
GermanLlama 3.1 Community

Open language model for chat and text. 2 sizes from 8B to 70.6B parameters.

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
1× H100 80 GB

The model needs about 7.4 GB of memory. Hopper, FP8 support.

Weights
4.8 GB
KV cache
1.1 GB
Speed
~191.7 Tok./s

More suitable configurations

CardQuantityTok./sStatus
Tesla T4 16 GB1×33.22-3 weeks delivery time
Tesla P100 16 GB1×41.82-3 weeks delivery time
Tesla P40 24 GB1×39.22-3 weeks delivery time
Tesla V100 16 GB1×92.4in stock
Tesla V100 32 GB1×92.4On order, delivery time approx. 1 week
AMD Instinct MI50 16 GB1×70.8in stock
AMD Instinct MI50 32 GB1×70.8in stock
AMD Instinct MI60 32 GB1×65.42-3 weeks delivery time
AMD Instinct MI100 32 GB1×79.12-3 weeks delivery time
A30 24 GB1×89.42-3 weeks delivery time
RTX A5000 24 GB1×93.12-3 weeks delivery time
A40 48 GB1×88.82-3 weeks delivery time