Run Mistral Large on-premises
○ Memory-fit arithmetic — checkable math, not a benchmark
Mistral Large is Europe's flagship open-weight model family — roughly 123 billion parameters of dense transformer, strong in French and across EU languages. For a regulated European business, running it on hardware you own is the cleanest sovereignty story available: a European model, on premises, under EU jurisdiction end to end.
The question buyers actually ask is narrower: does it fit? Here is the arithmetic against a machine with 128 GB of memory — a desktop AI unit, a workstation or a GPU server. The right machine for your workload is sized during the AI diagnostic.
Memory fit in 128 GB
| Parameters | ~123B (dense) |
|---|---|
| Full precision (FP16) | ~246 GB — needs a GPU server or a private cloud |
| 8-bit weights | ~123 GB — no working room left in 128 GB |
| 4-bit weights (the practical choice) | ~62–74 GB depending on the quantization |
| Reference memory | 128 GB (one machine) |
| Left for context cache + system at 4-bit | roughly 45–55 GB |
Every row is the same rule of thumb: parameters × bytes per parameter (FP16 ≈ 2, 8-bit ≈ 1, 4-bit ≈ 0.5), plus room for the KV cache that holds your context window. At 4-bit, Mistral Large fits a 128 GB machine with generous context headroom; at 8-bit it needs more memory — a larger workstation, a GPU server or a private cloud.
What it serves well
- French and EU-language drafting, analysis, and summarization at flagship quality.
- Private document analysis and retrieval (RAG) over contracts, dossiers, and archives that cannot leave the building.
- Assistants for regulated professions where an EU model on EU-controlled hardware is the requirement, not a preference.
- Multilingual customer-facing workflows served from your own machine.
Honest limits
- This page is memory arithmetic, not a benchmark; we size the machine for your workload during the AI diagnostic.
- Mistral publishes its weights under its own license terms; commercial deployment may require an agreement with Mistral AI. We cover licensing as part of the assessment.
- A dense 123B model produces tokens more slowly than sparse mixture-of-experts models of the same size class. If throughput matters more to you than the model's provenance, we will say so in the assessment.
Frequently asked questions
Does Mistral Large fit in 128 GB of memory?
Yes, quantized to 4-bit: about 62–74 GB of weights against 128 GB, leaving tens of gigabytes for the context cache and the system. Full-precision or 8-bit serving needs more memory — a larger workstation, a GPU server or a private cloud.
Is this page a benchmark?
No. This page is memory arithmetic, not a benchmark; we size the machine for your workload during the AI diagnostic.
Why run a European model on-premises rather than through a sovereign cloud API?
A hosted API still moves your prompts and documents to a third party's infrastructure. On your own machine, nothing leaves the building: the sovereignty argument becomes physical instead of contractual.
Find out which model fits your work
An AI diagnostic maps your processes, classes what is sensitive and sizes the model and the hardware against your real tasks.