qwen3.6

6.3M Downloads Updated 2 days ago

Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

vision tools thinking 27b 35b

ollama run qwen3.6

curl http://localhost:11434/api/chat \
  -d '{
    "model": "qwen3.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='qwen3.6',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'qwen3.6',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model qwen3.6

OpenCode ollama launch opencode --model qwen3.6

Hermes Agent ollama launch hermes --model qwen3.6

OpenClaw ollama launch openclaw --model qwen3.6

Models

View all →

Name

35 models

Size / Usage

Context

Input

qwen3.6:latest

23GB · 256K context window · Text, Image · 4 days ago

qwen3.6:latest

23GB

256K

Text, Image

qwen3.6:27b

18GB · 256K context window · Text, Image · 4 days ago

qwen3.6:27b

18GB

256K

Text, Image

qwen3.6:35b

latest

23GB · 256K context window · Text, Image · 4 days ago

qwen3.6:35b latest

23GB

256K

Text, Image

qwen3.6:27b-mlx

MLX

19GB · 256K context window · Text, Image · 2 days ago

qwen3.6:27b-mlx MLX

19GB

256K

Text, Image

qwen3.6:35b-mlx

MLX

24GB · 256K context window · Text, Image · 2 days ago

qwen3.6:35b-mlx MLX

24GB

256K

Text, Image

Readme

Following the February release of the Qwen3.5 series, we’re pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.

Qwen3.6 Highlights

This release delivers substantial upgrades, particularly in

Agentic Coding: the model now handles frontend workflows and repository-level reasoning with greater fluency and precision.
Thinking Preservation: we’ve introduced a new option to retain reasoning context from historical messages, streamlining iterative development and reducing overhead.