willitrun·ai

MistralMistral

Mistral Small 24B

Legacy
75.2KDescargas961Me gustaJan 2025Publicado33K tokensContextoMistral ResearchLicencia75 FuerteCalidad

Mistral Small 24B (24B parameters) requires approximately 18.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 22 GB of VRAM.

Comenzar

— copia y pega para ejecutar en local

Copy-paste commands to run Mistral Small 24B on your machine.

Run

ollama run mistral-small

Quick specs

Parameters24B
Architecturedense
Context33K tokens
Modalitytext
Min RAM9.4 GB
Rec. RAM14.6 GB (Q4_K_M)
LicenseMistral Research
FamilyMistral Small
Code Chat

About this model

Mistral Small 3 ( 2501 ) sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models! This model is an instruction-fine-tuned version of the base model: Mistral-Small-24B-Base-2501.

  • Multilingual:: Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch,...
  • Agent-Centric:: Offers best-in-class agentic capabilities with native function calling and JSON outputting
  • Advanced Reasoning:: State-of-the-art conversational and reasoning capabilities
  • Apache 2.0 License:: Open license allowing usage and modification for both commercial and non-commercial purposes
  • Context Window:: A 32k context window

Modelos relacionados

Tu hardware

Detectando...

Selecciones rápidas

Mejor hardware

Mejores opciones para Mistral Small 24B

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
9.4 GB
Low
Q3_K_S
3
11.8 GB
Low
NVFP4
4
13.4 GB
Medium
Q4_K_M
4
14.6 GB
Medium
Q5_K_M
5
17.3 GB
High
Q6_K
6
19.7 GB
High
Q8_0
8
25.7 GB
Very High
F16
16
49.2 GB
Maximum

Quality benchmarks

Mistral Small 24B benchmark scores

Benchmark verified

Coding

SWE-bench Verified
HumanEval+84.8%
Aider Polyglot
LiveCodeBench

Reasoning

MMLU-Pro66.3%
GPQA Diamond
MATH-50070.6%
ARC Challenge

General

Chatbot Arena
IFEval82.9%

Source: official · 2025-01-28

Compatibilidad de hardware

Estimaciones de encaje en todo el hardware

Abrir calculadora

Computing compatibility...

Desglose de memoria

Reference: RTX 2060 6GB

Weights14.6 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom0.6 GB

Preguntas frecuentes

FAQ — Mistral Small 24B

Ver también