huihui_ai/huihui-4:8b-q4

huihui_ai/ huihui-4:8b-q4_K

652 Downloads Updated 1 week ago

Huihui4-8B-A4B is a lightweight MoE (Mixture of Experts) conversational model optimized from Google's gemma-4-26B-A4B-it architecture

vision tools thinking 8b

ollama run huihui_ai/huihui-4:8b-q4_K

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/huihui-4:8b-q4_K",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/huihui-4:8b-q4_K',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/huihui-4:8b-q4_K',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 week ago

1 week ago

6351e4a67645 · 6.6GB ·

model

archgemma4

parameters8.67B

quantizationQ4_K_M

6.6GB

license

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

11kB

params

{ "temperature": 1, "top_k": 64, "top_p": 0.95 }

42B

template

13B

Readme

Huihui4-8B-A4B is a lightweight MoE (Mixture of Experts) conversational model optimized from Google’s gemma-4-26B-A4B-it architecture. Through expert pruning and supervised fine-tuning on high-quality dialogue data, this model significantly reduces computational overhead while preserving core reasoning and interaction capabilities. It is specifically designed for deployment on consumer-grade hardware and code-related conversational tasks.

This model is not an ablation variant.

Welcome everyone to test it.

References

[https://huggingface.co/huihui-ai/Huihui4-8B-A4B]