yanjia/qwopus3.5-9b:q8

yanjia/ qwopus3.5-9b:q8_0

576 Downloads Updated 1 month ago

Quantization based on Jackrong / Qwopus3.5-9B-v3

ollama run yanjia/qwopus3.5-9b:q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "yanjia/qwopus3.5-9b:q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='yanjia/qwopus3.5-9b:q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'yanjia/qwopus3.5-9b:q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

963f3dd70b47 · 9.5GB ·

model

archqwen35

parameters8.95B

quantizationQ8_0

9.5GB

system

You are a helpful assistant. You are also good at dealing with AI Agent.

72B

params

{ "num_ctx": 8192, "num_gpu": 99, "temperature": 0.7 }

48B

Readme

模型说明

本模型为 Jackrong/Qwopus3.5-9B-v3 的 GGUF 量化版本，使用 llama.cpp 转换制作。

Tag	量化方式	文件大小	推荐显存
Q8_0	8-bit 量化	~9.5 GB	≥ 12 GB

许可证

本模型继承原模型许可证：Apache 2.0

引用原模型

如在研究中使用，请引用原作者：

@misc{jackrong_qwen35_9b_v3, title = {Jackrong/Qwopus3.5-9B-v3}, author = {Jackrong}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/Jackrong/Qwopus3.5-9B-v3}} }

量化说明

原始模型由 llama.cpp convert_hf_to_gguf.py 转换为 F16 GGUF，再使用 llama-quantize 量化。量化过程未对模型权重做其他修改。