Mistral Small 4
A solid pick for self-hosting and full data control.
Overview
Mistral Small 4, released on 16 March 2026, is the first Mistral model to combine the abilities of its specialist models: Magistral's reasoning, Pixtral's multimodality and Devstral's agentic coding. Reasoning mode is switched on per request, so everyday tasks keep fast replies. Despite the name, it is a large model: a 119-billion-parameter Mixture-of-Experts with only 6.5 billion active per token and a 256k-token context. Mistral reports 40% lower latency and three times more requests per second than Small 3. It is Apache 2.0 licensed, with no commercial restriction, and published on Hugging Face with NVFP4 variants and a speculative-decoding head. It is Mistral's default choice for volume: assistants, document extraction, simple agents. For the most demanding tasks, Mistral Medium 3.5 takes over.
Skill profile
Not disclosed
Three independent measures
What people prefer, what the model can do, what the market uses. Each source has its biases and none is enough on its own: we show them side by side, never blended.
Strengths
- Has a free tier
- Open-source and self-hostable
- Competitive input pricing
Who is it for
- you want to control cost or self-host
- your data must stay in the EU
Ideal use cases
- High-volume assistants and chatbots
- Document extraction and analysis
- Cost-controlled simple agents
Access & availability
Key specifications
What it costs per month
Estimate from sourced API prices and a hardware tier for self-hosting. Assumptions are editable.
Assumptions: 36-month amortisation, 0.25 €/kWh, 22 days/month, 1 $ = 0.92 €. Excludes labour, software licences, redundancy.
nAIvigate Trust Index
What the vendor offers and documents for professional use in Europe. An undocumented criterion counts as zero and stays visible: the score rises when the vendor publishes, not when we assume.
19/19 criteria documented · 100 % · 12 of them set by rule
See the criteria▾
Trust Index badge
Show this score in your docs, README or security page. It updates automatically.
[](https://naivigate.com/en/model/mistral-small-4)Data & compliance
What we know, line by line, with source and date. These lines feed the Data and Enterprise families of the Trust Index above. GDPR compliance depends on your processing, not on the model alone.
| EU data residency | Yes |
| Data processing agreement (DPA) | N/A· self-hosted: data never leaves |
| Transfer outside the EU | No |
| Training on your data | No |
| Configurable retention | N/A· self-hosted: data never leaves |
| Zero Data Retention | N/A· self-hosted: data never leaves |
| Self-hostable | Yes |
| Declared hosting | EU |
| Anonymisable data | Yes |
Quality of this card’s data
This score measures the quality of the data on this card: price, context, Elo, licence, documented, sourced and fresh. It measures neither the model nor its compliance: for that, see the Trust Index above.
6/8 documented · 3/8 primary sources
Run it locally
| Quantization | Disk | RAM / VRAM | Typical hardware |
|---|---|---|---|
| Q4 · recommended | 67.8 GB | 77 GB | 96-128GB Mac Studio / 4× GPUs |
| Q8 · balanced | 127.3 GB | 142 GB | Server GPU infra (H100/A100…) |
| FP16 · max quality | 238 GB | 264 GB | Server GPU infra (H100/A100…) |
Estimates for a moderate context. Long contexts need more RAM (KV cache).
Deploy
Copy-ready commands generated from this card. Adjust context length and GPU count to your hardware.
OpenAI-compatible server for production on NVIDIA GPUs.
pip install vllm
vllm serve mistralai/Mistral-Small-4-119B-2603 \
--max-model-len 32768 \
--tensor-parallel-size 2 \
--dtype autoAdvanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
| Arena Elo | — |
| MMLU | — |
| GPQA | — |
| HumanEval | — |
| SWE-Bench | — |
| MATH | — |