bvassie/qwen3.6:35b-a3b-mtp

bvassie/ qwen3.6:35b-a3b-mtp

51 Downloads Updated 1 week ago

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

vision tools thinking

ollama run bvassie/qwen3.6:35b-a3b-mtp

curl http://localhost:11434/api/chat \
  -d '{
    "model": "bvassie/qwen3.6:35b-a3b-mtp",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='bvassie/qwen3.6:35b-a3b-mtp',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'bvassie/qwen3.6:35b-a3b-mtp',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 week ago

1 week ago

a3e0e2d12b6b · 22GB ·

model

archqwen35moe

parameters34.7B

quantizationQ4_K_M

20GB

projector

archclip

parameters447M

quantizationQ8_0

614MB

draft

GGUF��,��general.architecture�� qwen35moe��general.type��

1.1GB

params

{ "draft_num_predict": 4, "min_p": 0, "presence_penalty": 1.5, "repeat_penalty": 1,

116B

template

13B

Readme

Created using:

Modelfile:

FROM ./Qwen3.6-35B-A3B-Q4_K_M.gguf
FROM ./mmproj-Qwen3.6-35B-A3B-Q8_0.gguf
DRAFT ./mtp-Qwen3.6-35B-A3B-Q4_0.gguf
TEMPLATE {{ .Prompt }}
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER min_p 0
PARAMETER presence_penalty 1.5
PARAMETER repeat_penalty 1
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95
PARAMETER draft_num_predict 4