metalspork/qwen3.8-ud:Q8_K

metalspork/ qwen3.8-ud:Q8_K_XL

645 Downloads Updated 3 weeks ago

Unsloth Dynamic Quants for qwen3.8 27b

ollama run metalspork/qwen3.8-ud:Q8_K_XL

curl http://localhost:11434/api/chat \
  -d '{
    "model": "metalspork/qwen3.8-ud:Q8_K_XL",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='metalspork/qwen3.8-ud:Q8_K_XL',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'metalspork/qwen3.8-ud:Q8_K_XL',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 weeks ago

3 weeks ago

94aa9fed6bb7 · 31GB ·

model

archqwen35

parameters27.3B

quantizationQ4_K_M

31GB

params

{ "temperature": 0.7, "top_k": 20, "top_p": 0.95 }

44B

template

13B

Readme

This is simply a re-packaging of the Unsloth Dynamic Quants to make it easy to pull from ollama, with top_p 0.95, temp 0.7, top_k 20.

Upstream source: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF