← All modelsMODEL CHECK

Can I run Ministral 3 3B?

Ministral 3 3B by Mistral AI needs around 4 GB of RAM at the recommended 4-bit quantization (1.8 GB download). Your hardware is checked below — instantly, nothing leaves your browser. Expect roughly ~168 tok/s on a NVIDIA RTX 3060 12GB.

Reading your hardware signals…

Specifications

Parameters3B
Context window256K tokens
ProviderMistral AI
LicenseApache 2.0
Released2025-12
Best forChat, Vision

Size by quantization

QuantizationBits/weightDownloadMin RAMQuality
Q2_K3.351.3 GB4 GBNoticeable loss
Q4_K_MRecommended4.851.8 GB4 GBRecommended
Q5_K_M5.652.1 GB6 GBHigh
Q8_08.53.2 GB6 GBNear-original
F16166.0 GB12 GBOriginal

Sizes are estimates from parameter count × bits per weight; real GGUF builds vary slightly. · Data updated: 2026-06-11 · How we calculate these numbers →

Memory needed by context length

ContextKV cache (est.)Total memory (Q4)
4K tokens~0.3 GB~2.1 GB
8K tokens~0.7 GB~2.5 GB
32K tokens~2.7 GB~4.5 GB
128K tokens~10.8 GB~12.6 GB

The KV cache grows with context length — a model that fits at 4K can run out of memory at 32K. Estimates assume an FP16 cache with grouped-query attention; actual usage varies by runtime.

Estimated speed by hardware

HardwareBandwidth~Speed
NVIDIA RTX 3060 12GB360 GB/s~168 tok/s
NVIDIA RTX 4090 24GB1008 GB/s~471 tok/s
Apple M-series (base)100 GB/s~47 tok/s
Apple M-series Pro270 GB/s~126 tok/s
Apple M-series Max410 GB/s~192 tok/s
CPU only (dual-channel DDR5)60 GB/s~28 tok/s

Token generation is memory-bandwidth bound: tok/s ≈ bandwidth × 0.85 ÷ model size at Q4. Real-world numbers vary by runtime and context length.

Run it locally

The easiest path is Ollama — one command and you're chatting:

ollama run ministral-3:3b

Frequently asked questions