Building upon Mistral Small 3.2 (2506) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-t

vision tools

ollama run SimonPu/Mistral-Small-3.2:Q4_K_XL

curl http://localhost:11434/api/chat \
  -d '{
    "model": "SimonPu/Mistral-Small-3.2:Q4_K_XL",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='SimonPu/Mistral-Small-3.2:Q4_K_XL',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'SimonPu/Mistral-Small-3.2:Q4_K_XL',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 8 months ago

8 months ago

ab03e5e9fa00 · 15GB ·

model

archllama

parameters23.6B

quantizationQ4_K_M

15GB

projector

archclip

parameters439M

quantizationF16

878MB

system

You are Mistral Small 3.2, a Large Language Model (LLM) created by Mistral AI, a French startup head

2.4kB

params

{ "min_p": 0, "num_ctx": 40960, "repeat_penalty": 1, "stop": [ "</s>" ],

102B

template

{{- range $index, $_ := .Messages }} {{- if eq .Role "system" }}[SYSTEM_PROMPT]{{ .Content }}[/SYSTE

714B

Readme

Mistral-Small-3.2-24B-Instruct-2506

Mistral-Small-3.2-24B-Instruct-2506 is a minor update of Mistral-Small-3.1-24B-Instruct-2503.

Small-3.2 improves in the following categories: - Instruction following: Small-3.2 is better at following precise instructions - Repetition errors: Small-3.2 produces less infinite generations or repetitive answers - Function calling: Small-3.2’s function calling template is more robust (see here and examples)

In all other categories Small-3.2 should match or slightly improve compared to Mistral-Small-3.1-24B-Instruct-2503.

Key Features

same as Mistral-Small-3.1-24B-Instruct-2503