[email protected]

Devstral Hosting in Germany: Run Mistral's Coding Models Yourself

You want to run coding agents and IDE assistants on your own model without sending source code to a third-party API. We run Devstral on a dedicated GPU server in a German data centre.

  • Operated in a German data centre
  • Operation under a DPA
  • vLLM and OpenAI-compatible API
Reviews
Cloud Wolke HerausforderungServer NachhaltigkeitIT Beratung Service Consulting SoforthilfeTimo Wevelsiep Robin ZinsExperten für Innovation Migration AWSHetzner Hosting zuverlässig

Customers from mid-sized business, industry and the public sector, in Germany and internationally

  • Stadtwerke Brühl
  • DGHO e.V.
  • solarwerkstatt berlin
  • Krüger Dirndl
  • ABCO Water Systems
  • Golem.de
  • EVADXB
  • nextGYM
  • AInergy
  • ml&s
  • Odiseo Solutions
  • Annota
  • ARGE
  • SweetConnect GmbH
  • Aphy AG
  • CORGOS
  • Rekorder
  • SolidProof
  • Yonju
  • Keymate
  • Paritel
  • Mr. Clipart
  • Millenium
  • Negosh
  • Führerscheinmacher
  • BTI
  • Deutsche Gesellschaft für Datenschutz
Read client reviews

Starting point

Why run Devstral yourself

Devstral is Mistral AI's coding line. The models are designed for software development agents: exploring a codebase, editing several files and calling tools. Devstral Small 2 has 24B parameters, also accepts images and is licensed under Apache 2.0. Devstral 2 has 123B parameters and is licensed under a Modified MIT License with a revenue threshold. Coding agents send large parts of a codebase to the model as context. On your own server, source code, diffs and test output stay in the German data centre. IDE extensions and agent clients connect to the server through vLLM's OpenAI-compatible API. We cover the general-purpose models Mistral Small 4 and Mistral Medium 3.5 on the Mistral hosting page.

  • Data stays in Germany

    The model runs on a dedicated server in a German data centre. Under a data processing agreement, with no data path to a model API.

  • Predictable costs

    A fixed monthly price per server tier instead of billing per consumed token. More requests do not increase the invoice.

  • Model version under control

    Checkpoint and quantisation stay until you agree to a change. No silent model update by a provider.

Model facts

Devstral checkpoints at a glance

Vendor specifications and weight file size per format, with source.

CheckpointReleasedParametersContext (vendor)Weights per format
mistralai/Devstral-Small-2-24B-Instruct-251212/202524B (dense, with vision)256K tokensFP8: 25.8 GB
mistralai/Devstral-2-123B-Instruct-251212/2025123B (dense, text only)256K tokensFP8: 128.2 GB
  • GB = 10⁹ bytes, sum of the weight files in the listed Hugging Face repository. Operation additionally needs memory for KV cache, runtime and image processing where applicable. As of October 2026.

Licence

Devstral: licence and commercial use

Licence

Apache 2.0 (Devstral Small 2) / Modified MIT (Devstral 2) (Licence text, Devstral Small 2 model card)

  • Commercial use: Devstral Small 2: yes, without a revenue or user threshold. Devstral 2: only if the consolidated global monthly revenue of your company (or your employer) did not exceed USD 20 million in the preceding month.
  • Obligations and thresholds: Modified MIT: include attribution and the licence notice. Above the revenue threshold the licence grants no rights, including for derived or combined models; Mistral AI grants commercial licences on request. Apache 2.0: include the licence text and notices when redistributing.
  • Checked: As of October 2026

Technical classification, not legal advice. The licence text of the deployed model version is authoritative. Open LLM licences compared

Server tier

Minimum recommended server tier for Devstral

The recommendation follows from the weight size plus headroom for context and runtime.

ModelFormatWeightsMinimum recommendedNote
Devstral Small 2FP825.8 GBManaged GPU Server 96The weights alone exceed 24 GB. The headroom on 96 GB goes into context and concurrent agent runs.
Devstral 2FP8128.2 GBManaged GPU Server 192Licence note: no rights above USD 20 million consolidated monthly company revenue.
  • Which tier suits your use case depends on context length and concurrent requests. We check this before the proposal.
  • Mistral publishes both models as FP8 checkpoints. The repositories also contain the weights a second time in consolidated format, which is not loaded twice in operation.

Pricing

The Managed GPU Server tiers

Managed GPU Server 24

1 × RTX PRO 4000 Blackwell, 24 GB GPU memory

€699 excl. VAT / monthcancellable monthly€499 excl. VAT one-time setup

Relevant for this family

Managed GPU Server 96

1 × RTX PRO 6000 Blackwell Max-Q, 96 GB GPU memory

€2,199 excl. VAT / monthcancellable monthly€1,999 excl. VAT one-time setup

Relevant for this family

Managed GPU Server 192

2 × RTX PRO 6000 Blackwell Max-Q, 192 GB GPU memory

Price and term on request

Managed GPU Server 384

4 × RTX PRO 6000 Blackwell Max-Q, 384 GB GPU memory

Price and term on request

The Managed GPU Server 288 with three GPUs is intended for several models side by side, because vLLM only splits a model when the attention heads are divisible by the number of GPUs.

All prices are net and exclude statutory VAT. The offers are addressed to businesses.

Payment
  • SEPA direct debit
  • Visa
  • Mastercard
  • American Express
  • Apple Pay
  • Google Pay
  • PayPal
  • Bank transfer

vLLM

Running Devstral with vLLM

Architecture, quantisation and distribution across several GPUs.

Architectures

Devstral Small 2 uses Mistral3ForConditionalGeneration with an image encoder, Devstral 2 the text-only architecture Ministral3ForCausalLM. Both are listed among the models supported by vLLM. Mistral requires mistral_common version 1.8.6 or later for serving.

Tool calling for agents

Coding agents call tools via function calling. vLLM enables this for Devstral with the mistral tool-call parser and automatic tool choice, as described in the model card. Clients with an OpenAI-compatible interface use it via base URL and API key.

Context and concurrent agents

Every agent run keeps its context in the KV cache. Long contexts and many concurrent runs share the same GPU memory. Mistral's own example serves Devstral Small 2 with the full 262,144 tokens on two GPUs. On one GPU we set context length and parallel runs to suit your team.

Tensor parallelism

Devstral Small 2 has 32 attention heads and Devstral 2 has 96, both with 8 KV heads. Both can be split across two or four GPUs. Mistral's example for Devstral 2 uses eight GPUs; for the FP8 weights of around 128 GB we recommend at least two RTX PRO 6000.

Operated by WZ-IT

What operation includes

The Managed GPU Server is an operated model environment, not an empty server.

View Managed GPU Server
Model and API
  • Model and vLLM

    An agreed model in the agreed quantisation, served through a managed vLLM inference layer.

  • OpenAI-compatible API

    Applications and coding clients connect to the server via base URL and API key.

Interface and monitoring
  • Open WebUI

    A managed chat interface for teams using the model without their own application.

  • 24/7 monitoring

    Host, GPU, vLLM and Open WebUI are monitored proactively; incidents are handled according to the service level.

Maintenance and contract
  • Updates with CVE assessment

    Operating system, drivers, vLLM and Open WebUI are reviewed and updated in a controlled way. Model changes only by agreement.

  • DPA and documentation

    Data processing agreement, documented configuration and a personal point of contact.

Scope, prices and multi-GPU servers are on the product page.

Frequently asked questions about Devstral hosting

Licence, server tier, data path and operation

Reviews & projects

What clients say about working with us

From a knowledge base with an AI assistant and local AI integration to data sovereignty and ongoing operations.

AI Platform

We were looking for a secure yet easy-to-use alternative to the large American providers and came across WZ-IT. WZ-IT advised us on choosing the right models and implemented the integration for us. Beforehand, we were able to try everything out calmly on a test instance. Today WZ-IT runs Open WebUI for us on our own domain, with a convenient Microsoft login and open-source models hosted by a German provider. Our team can now work productively with AI without resorting to external tools or shadow AI. Working together is straightforward, and questions are answered quickly and clearly. With WZ-IT we also have a partner at our side for further AI projects. (translated)
Carl-Frederic KornHead of E-Commerce & Online Marketing, Krüger Dirndl GmbH
See the AI platform

Knowledge Management & AI

The knowledge from many years in the solar industry lived in the head of our former managing director, and it still lives in the heads of our employees today. We wanted to secure it, not as a folder full of notes, but in a way that lets us ask questions in daily work and get reliable answers. WZ-IT advised us from the start and weighed different approaches and knowledge management systems against each other with us before we decided. What was built is a custom knowledge base with an AI assistant that brings together conversations, notes, documentation and manuals: from the platform through onboarding our team to support in operation. Conversations are transcribed and facts are extracted; we review and correct everything ourselves before it is stored, because we do not want to trust an AI blindly. The system runs in our own environment, and the data stays with us. What surprised us was how efficient it was: WZ-IT used existing open-source software and extended it specifically for our requirements, instead of selling an expensive custom build from scratch, as is often usual with IT service providers. Timo and Robin understood our actual problem, preserving knowledge during the generational handover, and implemented it step by step: from the proof of concept through setup and validation with our own data to productive operation, explaining everything clearly along the way. Next, we want to extend this to the knowledge of our employees, so that this does not depend on individual people either.
Joshua von AmelnManaging Director, solarwerkstatt berlin GmbH
See knowledge transfer

Read client reviews

International

Selected projects

WZ-IT designs, develops and operates infrastructure and software for clients in Germany and internationally. We deliver projects remotely and continue supporting them in ongoing operations after go-live.

Model assessment

Have your model and server tier assessed

Name the model, context length and concurrent requests. We check checkpoint, licence and server tier before the proposal.

  • You speak directly with Timo and Robin, who are technically responsible
  • A professional assessment of your situation
  • Concrete next steps for infrastructure, software or AI

The conversation is free and non-binding.

WZ-IT's advice on our Azure migration was technically sound and completely non-binding right from the intro call - we took away a great deal.
Jakob ÖschlbergerInno7 GmbH
Timo and Robin, founders of WZ-IT

Which server tier should be assessed?

The selection is non-binding. We confirm model fit, licence and term before a proposal.

We usually respond within one business day. Please do not send access credentials yet.

WZ-IT's advice on our Azure migration was technically sound and completely non-binding right from the intro call - we took away a great deal.
Jakob ÖschlbergerInno7 GmbH