AI-TAVS/Qwen3.8-dau

AI-TAVS/ Qwen3.8-dau:latest

72 Downloads Updated 5 days ago

Model exceeds all Qwen 3.8, 3.6 and 3.5 27B critical core benchmarks. A model that gets down to business faster, with less "talking" and is smarter too.

vision 27b

ollama run AI-TAVS/Qwen3.8-dau

curl http://localhost:11434/api/chat \
  -d '{
    "model": "AI-TAVS/Qwen3.8-dau",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='AI-TAVS/Qwen3.8-dau',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'AI-TAVS/Qwen3.8-dau',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 days ago

5 days ago

e7496bf56cec · 19GB ·

model

archqwen35

parameters26.9B

quantizationQ4_K_M

18GB

projector

archclip

parameters461M

quantizationF16

928MB

Readme

Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF

The COLD FUSION (GAIN+Unsloth) method of training maintains 99% of performance of BF16, at both 8 bit and 4 bit levels. Model exceeds all Qwen 3.8, 3.6 and 3.5 27B critical core benchmarks. A model that gets down to business faster, with less “talking” and is smarter too.

Detail: https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF