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

Which card for which language model?

A language model needs enough graphics memory (VRAM) for the model and its context. This table gives guide values.

Tip
For a specific model, our model calculator tells you the suitable card.

Guide values by model size

Small, up to 10 bn.
Examples
Qwen3.5 4B and 9B, Gemma 4 E4B, Granite 4.2 8B, Llama 3.1 8B
Recommendation
Tesla T4 16 GB or V100 16 GB
Medium, 14 to 32 bn.
Examples
Qwen3.8 27B, Gemma 4 31B, GLM-4.7-Flash, gpt-oss-20b
Recommendation
Tesla V100 32 GB
Large, from 70 bn.
Examples
Llama 3.3 70B, Apertus 70B, gpt-oss-120b
Recommendation
A100 80 GB or 2× V100 32 GB
Very large, from 120 bn.
Examples
Kimi K3, DeepSeek V4 Pro, GLM 5.3, Qwen3.5 397B
Recommendation
Server with several A100 80 GB or H100, on request
  • With 4-bit quantization, models up to about 40 bn. parameters fit on a V100 32 GB.
  • Llama 3.3 70B needs about 46 GB in 4-bit with 8k context.
  • Several cards share the model, but do not become faster as a result.

Quantization

Models usually come in 16-bit precision. With quantization (e.g. 4 bit) the memory requirement drops to about a third, with little loss in quality.

FormatUsed in
Q4_K_Mllama.cpp, Ollama
AWQ / GPTQvLLM, Transformers

Context and speed

TermMeaning
Context (e.g. 8k, 32k, 128k tokens)How much text the model keeps in view at once. More context needs more VRAM and makes it slower.
Token speedDepends on the memory bandwidth of the card. A V100 manages about 25 tokens/s with a 32B model.

For individual advice or server configurations, get in touch with us.