LLM
GA
Open weights
Mistral Small 4
Fast, commercially usable assistant on a single 24 GB GPU
Release2026-09
Context131K
Max output—
Parameters24B
Local / VRAM16–24 GB
LicenseOpen weights
Overview
Mistral Small 4 is a model in the LLM category from Mistral AI. It was released in 2026-09. The vendor is based in France. Best for: Fast, commercially usable assistant on a single 24 GB GPU.
Strengths
- Apache-2.0
- 24 GB class
- Fast
Limits
- No frontier reasoning
- 131K context
Specifications
| Vendor | Mistral AI |
|---|---|
| Category | LLM |
| Release | 2026-09 |
| Status | GA |
| License | Open weights |
| License name | Apache-2.0 |
| Commercial use | Allowed |
| Parameters | 24B |
| Architecture | dense transformer |
| Context window | 131K |
| Input modalities | Text, Image |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 16–24 GB |
| System RAM | 32–64 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | Medium |
| Vendor country | France |
| Vendor type | Frontier lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 16–24 GB. Approximate system RAM: 32–64 GB. API access is available.