MONSDER / REFERENCE SYSTEMS

Ready solutions for popular models

Choose a reference profile. The current engineering kernel recalculates it and shows a complete new-hardware system.

01

Choose a scenario

These are fixed inputs, not a model ranking.

02

Local AI assistant

Adjust in calculator

Model: Qwen/Qwen3-8B
Workload: INT4 · 8,192 tokens · 1 concurrent
Result source: Current calculation kernel and catalog

Recalculating the reference profile…

How to plan AI hardware

How much VRAM does an LLM need?
Estimate LLM memory from weights, quantization, KV cache, context and concurrency. An 8B example and the limits of a preliminary Monsder calculation.
How to choose an AI server
Choose an AI server from workload requirements: model, load, GPU, memory, power and cooling. What a calculator estimates and what needs engineering validation.
Which models fit your GPU?
Match an LLM to your GPU using available VRAM, quantization, context and concurrency. Why fitting in memory does not establish a validated deployment.