gbox
Vos données restent chez vous. Book a demo
← Back to the AI Box Supported models

Which LLM in your box?

All supported models are open-source or shipped under a clear commercial licence. You can run several in parallel and switch any time.

★ Recommended
Gemma 4 31B
Google DeepMind

The default model on M and L. Excellent reasoning and writing quality across many languages.

Parameters
31B
Context
128k
Licence
Gemma
Strengths : Multilingual (135+ languages) · reasoning · summarisation · 128k context
S M L
Fits on
Gemma 4 9B
Google DeepMind

The smaller sibling: fits on the S, solid performance for everyday tasks.

Parameters
9B
Context
128k
Licence
Gemma
Strengths : Lightweight · fast · very usable in any major language
S M L
Fits on
Mistral Large 2
Mistral AI

High-end French-trained model. Excellent for long-form writing and complex reasoning.

Parameters
123B
Context
128k
Licence
MRL
Strengths : Quality writing · reasoning · 128k context · made in France
S M L
Fits on
Mistral Small 3
Mistral AI

Good perf/cost trade-off when you don't need the Large.

Parameters
24B
Context
32k
Licence
Apache
Strengths : Fast · solid French · Apache 2.0 (free use)
S M L
Fits on
Llama 3 70B
Meta

Meta's reference model: massive global adoption, mature ecosystem.

Parameters
70B
Context
128k
Licence
Llama
Strengths : Excellent English · solid French · strong public benchmarks
S M L
Fits on
Llama 3 8B
Meta

Compact Llama 3: fits on the S, great for high-volume usage.

Parameters
8B
Context
128k
Licence
Llama
Strengths : Fast · stable · widely integrated with third-party tooling
S M L
Fits on
Qwen 2.5 72B
Alibaba Cloud

High-performance Chinese model. Pick this for complex multilingual scenarios.

Parameters
72B
Context
128k
Licence
Qwen
Strengths : Top-tier multilingual · reasoning · code
S M L
Fits on
Codestral 22B
Mistral AI

Code-specialised. Powers the Code Reviewer module for tech teams.

Parameters
22B
Context
32k
Licence
MNPL
Strengths : Code (80+ languages) · refactoring · auto-documentation
S M L
Fits on
Whisper Large v3
OpenAI (open weights)

Multilingual audio transcription. Powers the Meeting Summarizer module.

Parameters
1.5B
Context
—
Licence
MIT
Strengths : Accurate transcription · French + 99 other languages · streaming
S M L
Fits on
Model management

You stay in control of what runs

🎯
Pick at install time
During initial deployment we configure the 2 or 3 main models for your use cases. Others are downloadable on demand.
🔄
Swap any time
Admin can enable or disable a model in a few clicks. No restart. No data migration.
📊
Benchmark in-house
Admin console with automated tests on your own prompts. Compare Gemma vs Mistral vs Llama on your real cases.
Custom model

A proprietary model to integrate?

You fine-tuned an internal model, or want to integrate one not on the list (Falcon, Phi, DeepSeek, etc.)? We add it to your box. Typical lead time: 2 weeks.

Discuss your model