sharky172/qwen3.6

sharky172/ qwen3.6

851 Downloads Updated 2 weeks ago

Qwen 3.6, MTP-enabled, 512k context (20GB KV cache footprint with OLLAMA_KV_CACHE_TYPE=q8_0)

ollama run sharky172/qwen3.6:27b-mtp-q4_K_M-512k

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sharky172/qwen3.6:27b-mtp-q4_K_M-512k",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sharky172/qwen3.6:27b-mtp-q4_K_M-512k',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sharky172/qwen3.6:27b-mtp-q4_K_M-512k',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

4 models

Size / Usage

Context

Input

qwen3.6:27b-mtp-q4_K_M-512k

17GB · 512K context window · Text · 2 weeks ago

qwen3.6:27b-mtp-q4_K_M-512k

17GB

512K

Text

qwen3.6:27b-mtp-q8_0-512k

29GB · 512K context window · Text · 2 weeks ago

qwen3.6:27b-mtp-q8_0-512k

29GB

512K

Text

qwen3.6:35b-a3b-mtp-q4_K_M-512k

22GB · 512K context window · Text · 2 weeks ago

qwen3.6:35b-a3b-mtp-q4_K_M-512k

22GB

512K

Text

qwen3.6:35b-a3b-mtp-q8_0-512k

38GB · 512K context window · Text · 2 weeks ago

qwen3.6:35b-a3b-mtp-q8_0-512k

38GB

512K

Text

Readme

No readme