qwen3.8:27b-mtp-q8

qwen3.8:27b-mtp-q8_0

9,597 Downloads Updated 4 hours ago

Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

vision tools thinking 27b

ollama run qwen3.8:27b-mtp-q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "qwen3.8:27b-mtp-q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='qwen3.8:27b-mtp-q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'qwen3.8:27b-mtp-q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 4 hours ago

4 hours ago

8a1582877303 · 30GB ·

model

archqwen35

parameters27.3B

quantizationQ8_0

29GB

projector

archclip

parameters461M

quantizationBF16

931MB

license

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

11kB

params

{ "draft_num_predict": 4, "min_p": 0, "presence_penalty": 0, "repeat_penalty": 1,

114B

Readme

Qwen3.8 Highlights

Qwen3.8-27B features the following enhancements:

Core Capabilities: Comprehensive improvements across coding, professional work, research, and long-horizon agentic tasks.
Agent Execution: Stronger autonomous planning and better handling of environment feedback, leading to more reliable end-to-end task completion.
Downstream Compatibility: Broader support for popular harnesses and development tools, making it easier to integrate into your existing stack.
Flexible Thinking Control: Thinking mode is on by default and can be disabled per request; reasoning depth can be tuned with reasoning_effort, and reasoning context from historical messages is retained via preserve_thinking.
Vision-Language Understanding: Native support for image and video understanding, from STEM diagrams and documents to hour-scale videos.

Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

Details

Readme

Qwen3.8 Highlights

Benchmark