Ministral 3 — local AI model by Mistral AI
Written by Jakub Rusinowski · Last updated
The edge tier of the Mistral 3 family — 3B, 8B and 14B dense, every size shipped in base, instruct and reasoning variants with image understanding, all Apache 2.0. Built for laptops, phones, drones and anywhere a datacenter is not. The 3B runs in about 4 GB of video memory; the 14B reasoning variant scores 85% on AIME 2025.
Variants
The smallest Ministral 3 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 3 3B → 3B | ~2.6 GB | 131,072 | ollama run ministral-3:3b | |
| Ministral 3 8B → 8B | ~5.6 GB | 131,072 | ollama run ministral-3:8b | |
| Ministral 3 14B → 14B | ~9.3 GB | 131,072 | ollama run ministral-3:14b |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Ministral 3 locally
Install Ollama, then pull the tag.
ollama run ministral-3:3bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Ministral 3 3B, Ministral 3 8B, Ministral 3 14BRecommended GPU
The cheapest catalogued GPU that runs Ministral 3 locally (min 3 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run Ministral 3 on my GPU?
- Ministral 3 on AMD Radeon RX 7800 XT
- Ministral 3 on AMD Radeon RX 7900 XT
- Ministral 3 on AMD Radeon RX 9060 XT 16GB
- Ministral 3 on AMD Radeon RX 9060 XT 8GB
- Ministral 3 on AMD Radeon RX 9070
- Ministral 3 on AMD Radeon RX 9070 XT
- Ministral 3 on Apple M1
- Ministral 3 on Intel Arc B570
- Ministral 3 on Intel Arc B580
- Ministral 3 on NVIDIA GeForce RTX 3060 (12GB)
- Ministral 3 on NVIDIA GeForce RTX 3070
- Ministral 3 on NVIDIA GeForce RTX 3070 Ti
- Ministral 3 on NVIDIA GeForce RTX 3080 (10GB)
- Ministral 3 on NVIDIA GeForce RTX 4060
- Ministral 3 on NVIDIA GeForce RTX 4060 Ti 16GB
- Ministral 3 on NVIDIA GeForce RTX 4070
- Ministral 3 on NVIDIA GeForce RTX 4070 Super
- Ministral 3 on NVIDIA GeForce RTX 4070 Ti
- Ministral 3 on NVIDIA GeForce RTX 4070 Ti Super
- Ministral 3 on NVIDIA GeForce RTX 4080
- Ministral 3 on NVIDIA GeForce RTX 4080 Super
- Ministral 3 on NVIDIA GeForce RTX 5060
- Ministral 3 on NVIDIA GeForce RTX 5060 Ti 16GB
- Ministral 3 on NVIDIA GeForce RTX 5060 Ti 8GB
- Ministral 3 on NVIDIA GeForce RTX 5070
- Ministral 3 on NVIDIA GeForce RTX 5070 Ti
- Ministral 3 on NVIDIA GeForce RTX 5080
Ministral 3 — frequently asked questions
How much VRAM does Ministral 3 need?
Ministral 3 needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Ministral 3 3B (3 GB, Q4_K_M); Ministral 3 8B (6 GB, Q4_K_M); Ministral 3 14B (9 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Ministral 3 on an RTX 4090 (24 GB)?
Yes — Ministral 3 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 3?
Q4_K_M is the best balance of quality and VRAM for Ministral 3 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 3 with Ollama?
Install Ollama, then run: ollama run ministral-3:3b. This downloads Ministral 3 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.