huihui_ai/huihui3.5:67b

huihui_ai/ huihui3.5:67b

216 Downloads Updated 1 week ago

Huihui 3.5 is a family of models created by remixing and merging multiple Qwen3.5 models of the same size.

vision tools thinking 67b

ollama run huihui_ai/huihui3.5:67b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/huihui3.5:67b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/huihui3.5:67b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/huihui3.5:67b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 week ago

1 week ago

d12601d8850a · 89GB ·

model

archqwen35moe

parameters136B

quantizationQ4_K_M

89GB

template

13B

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "temperature": 1, "top_k": 20, "top_p": 0.95 }

42B

Readme

Huihui 3.5:67B is a merged model created by combining Qwen/Qwen3.5-35B-A3B and Hcompany/Holo3-35B-A3B. The base model is Qwen/Qwen3.5-35B-A3B, and the total number of experts has been expanded from 256 to 512 experts, while still activating only 8 experts per token.

Note Huihui 3.5:67B is not an ablated model.

Welcome everyone to test it. If you require the unquantized model, please send an email to support@huihui.ai.

References

Qwen/Qwen3.5-35B-A3B Hcompany/Holo3-35B-A3B