bvassie/gemma4:31b-it-qat-dflash

bvassie/ gemma4:31b-it-qat-dflash

97 Downloads Updated yesterday

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

vision tools thinking

ollama run bvassie/gemma4:31b-it-qat-dflash

curl http://localhost:11434/api/chat \
  -d '{
    "model": "bvassie/gemma4:31b-it-qat-dflash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='bvassie/gemma4:31b-it-qat-dflash',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'bvassie/gemma4:31b-it-qat-dflash',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated yesterday

yesterday

a05991a0e67d · 20GB ·

model

archgemma4

parameters30.7B

quantizationQ4_0

18GB

projector

archclip

parameters576M

quantizationQ8_0

810MB

draft

GGUF��:��#��general.architecture��dflash��general.type��

1.6GB

params

{ "temperature": 1, "top_k": 64, "top_p": 0.95 }

42B

template

13B

Readme

Created using:

Modelfile:

FROM ./gemma-4-26B-A4B-it-Q4_0.gguf
FROM ./mmproj-gemma-4-26B-A4B-it-Q8_0.gguf
DRAFT ./mtp-gemma-4-26B-A4B-it-Q4_0.gguf
TEMPLATE {{ .Prompt }}
RENDERER gemma4
PARSER gemma4
PARAMETER top_k 64
PARAMETER top_p 0.95
PARAMETER temperature 1