VOOZH about

URL: https://willitrunai.com/models/ministral-3-8b

โ‡ฑ Ministral 3 8B VRAM Requirements โ€” GPU Compatibility


๐Ÿ‘ Mistral
Mistral

Ministral 3 8B

Frontier
๐Ÿ‘ huggingface
HuggingFace
134.8KDownloads177LikesOct 2025Released262K tokensContextApache 2.0License72 StrongQuality

Ministral 3 8B (8B parameters) requires approximately 10.1 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 12 GB of VRAM.

Get started

โ€” copy & paste to run locally

Copy-paste commands to run Ministral 3 8B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \ --hf-repo "mistralai/Ministral-3-8B-Instruct-2512" \ --hf-file "Ministral-3-8B-Instruct-2512-Q4_K_M.gguf" \ -c 4096 -ngl 99

Quick specs

Parameters8B
Architecturemultimodal
Context262K tokens
Modalitytext+vision
Min RAM3.1 GB
Rec. RAM4.9 GB (Q4_K_M)
LicenseApache 2.0
FamilyMinistral
โœ“ Visionโœ“ Chat

About this model

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

  • โ€ข8.4B Language Model
  • โ€ข0.4B Vision Encoder
  • โ€ขVision: Enables the model to analyze images and provide insights based on visual content, in addition to text
  • โ€ขMultilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic
  • โ€ขSystem Prompt: Maintains strong adherence and support for system prompts

Related models

Your hardware

Detecting...

Quick picks

๐Ÿ‘ Intel
Best budgetA
Intel Arc B580 12GB~$249 โ€” 48 tok/s
๐Ÿ‘ NVIDIA
Best overallS
RTX 4070 Ti Super 16GB~$799 โ€” 112 tok/s

Best hardware

Top picks for Ministral 3 8B

RTX 4070 Ti Super 16GBS
16 GB
RTX 4080 Super 16GBS
16 GB
RTX 4090 Laptop 16GBS
16 GB
RTX 5070 Ti 16GBS
16 GB
RTX 5080 16GBS
16 GB

Run this model

Ministral 3 8B on RTX 4070 Ti Super 16GBMinistral 3 8B on RTX 4080 Super 16GBMinistral 3 8B on RTX 4090 Laptop 16GB

Quantization options

VRAM estimates by quant level

No hardware detected โ€” fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
3.1 GB
Lowโ€”
Q3_K_S
3
3.9 GB
Lowโ€”
NVFP4
4
4.5 GB
Mediumโ€”
Q4_K_M
4
4.9 GB
Mediumโ€”
Q5_K_M
5
5.8 GB
Highโ€”
Q6_K
6
6.6 GB
Highโ€”
Q8_0
8
8.6 GB
Very Highโ€”
F16
16
16.4 GB
Maximumโ€”

Quality benchmarks

Ministral 3 8B benchmark scores

Benchmark verified

Reasoning

MMLU-Proโ€”
GPQA Diamond39.9%
MATH-500โ€”
ARC Challenge88.0%

Source: official ยท 2025-12-01

Hardware compatibility

Fit estimates across all hardware

Open calculator

Computing compatibility...

Memory breakdown

Reference: RTX 2060 6GB

Weights4.9 GB
KV Cache2.2 GB
Runtime2.4 GB
Headroom0.6 GB

Frequently asked questions

FAQ โ€” Ministral 3 8B

See also

Quantization GuideScoring MethodologyVRAM Calculator