Ministral — local AI model by Mistral AI
Written by Jakub Rusinowski · Last updated
Mistral AI's lightweight model family for resource-constrained environments. Ministral 8B punches well above its weight on reasoning tasks and fits on any GPU with 6 GB VRAM. Ministral 3B is designed for phones and edge devices.
Variants
The smallest Ministral variant needs about 3 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Ministral 3B → 3B | ~3 GB | 32,768 | ollama run ministral:3b | |
| Ministral 8B → 8B | ~5.6 GB | 32,768 | ollama run ministral:8b |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Ministral locally
Install Ollama, then pull the tag.
ollama run ministral:3bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
Applies to: Ministral 3B, Ministral 8BRecommended GPU
The cheapest catalogued GPU that runs Ministral locally (min 3 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run Ministral on my GPU?
- Ministral on AMD Radeon RX 9060 XT 8GB
- Ministral on Intel Arc B570
- Ministral on Intel Arc B580
- Ministral on NVIDIA GeForce RTX 3060 (12GB)
- Ministral on NVIDIA GeForce RTX 3070
- Ministral on NVIDIA GeForce RTX 3070 Ti
- Ministral on NVIDIA GeForce RTX 3080 (10GB)
- Ministral on NVIDIA GeForce RTX 4060
- Ministral on NVIDIA GeForce RTX 4070
- Ministral on NVIDIA GeForce RTX 4070 Super
- Ministral on NVIDIA GeForce RTX 4070 Ti
- Ministral on NVIDIA GeForce RTX 5060
- Ministral on NVIDIA GeForce RTX 5060 Ti 8GB
- Ministral on NVIDIA GeForce RTX 5070
Ministral — frequently asked questions
How much VRAM does Ministral need?
Ministral needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Ministral 3B (3 GB, Q4_K_M); Ministral 8B (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Ministral on an RTX 4090 (24 GB)?
Yes — Ministral runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Ministral?
Q4_K_M is the best balance of quality and VRAM for Ministral in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Ministral with Ollama?
Install Ollama, then run: ollama run ministral:3b. This downloads Ministral and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.