second_constantine/ruadapt-qwen3:32b

second_constantine/ ruadapt-qwen3:32b

105 Downloads Updated 6 months ago

GGUF Ruadapt версии модели Qwen/Qwen3-32B (квантизованная версия Q4_K_M)

tools thinking 32b

ollama run second_constantine/ruadapt-qwen3:32b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "second_constantine/ruadapt-qwen3:32b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='second_constantine/ruadapt-qwen3:32b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'second_constantine/ruadapt-qwen3:32b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 6 months ago

6 months ago

cd471ffad755 · 20GB ·

model

archqwen3

parameters32.7B

quantizationQ4_K_M

20GB

template

{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la

1.7kB

params

{ "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_end|>" ], "te

120B

Readme

Основано на https://huggingface.co/RefalMachine/RuadaptQwen3-32B-Instruct-GGUF

Характеристика	Значение
VLM	false
think	true
tools	true
speed	31 token/s

Характеристики примерные, проверялось на rtx3090 24GB