Will It Run AI

MistralMistral

Ministral 3 14B

Frontera
88.9KDescargas289Me gustaOct 2025Publicado262K tokensContextoApache 2.0Licencia82 FuerteCalidad

Ministral 3 14B (14B parameters) requires approximately 14.0 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 17 GB of VRAM.

Comenzar

— copia y pega para ejecutar en local

Copy-paste commands to run Ministral 3 14B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \ --hf-repo "mistralai/Ministral-3-14B-Instruct-2512" \ --hf-file "Ministral-3-14B-Instruct-2512-Q4_K_M.gguf" \ -c 4096 -ngl 99

Quick specs

Parameters14B
Architecturemultimodal
Context262K tokens
Modalitytext+vision
Min RAM5.5 GB
Rec. RAM8.5 GB (Q4_K_M)
LicenseApache 2.0
FamilyMinistral
Vision Chat

About this model

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.

  • 13.5B Language Model
  • 0.4B Vision Encoder
  • Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text
  • Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic
  • System Prompt: Maintains strong adherence and support for system prompts

Modelos relacionados

Tu hardware

Detectando...

Selecciones rápidas

Mejor hardware

Mejores opciones para Ministral 3 14B

Ejecutar este modelo

Opciones de cuantización

Estimaciones de VRAM por nivel de cuantización

No hardware detected — fit column shows raw VRAM estimates

QuantBitsVRAMQualityFit
Q2_K
2
5.5 GB
Low
Q3_K_S
3
6.9 GB
Low
NVFP4
4
7.8 GB
Medium
Q4_K_M
4
8.5 GB
Medium
Q5_K_M
5
10.1 GB
High
Q6_K
6
11.5 GB
High
Q8_0
8
15.0 GB
Very High
F16
16
28.7 GB
Maximum

Quality benchmarks

Ministral 3 14B benchmark scores

Benchmark verified

Reasoning

MMLU-Pro
GPQA Diamond39.9%
MATH-500
ARC Challenge89.9%

Source: official · 2025-12-01

Compatibilidad de hardware

Estimaciones de encaje en todo el hardware

Abrir calculadora

Computing compatibility...

Desglose de memoria

Reference: RTX 2060 6GB

Weights8.5 GB
KV Cache2.4 GB
Runtime2.4 GB
Headroom0.6 GB

Preguntas frecuentes

FAQ — Ministral 3 14B

Ver también