gemma4:31b-mtp-vision-bf16

vision tools thinking

ollama run home-rag/gemma4:31b-mtp-vision-bf16

curl http://localhost:11434/api/chat \
  -d '{
    "model": "home-rag/gemma4:31b-mtp-vision-bf16",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='home-rag/gemma4:31b-mtp-vision-bf16',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'home-rag/gemma4:31b-mtp-vision-bf16',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model home-rag/gemma4:31b-mtp-vision-bf16

OpenCode ollama launch opencode --model home-rag/gemma4:31b-mtp-vision-bf16

Hermes Agent ollama launch hermes --model home-rag/gemma4:31b-mtp-vision-bf16

OpenClaw ollama launch openclaw --model home-rag/gemma4:31b-mtp-vision-bf16

Models

View all →

Name

1 model

Size / Usage

Context

Input

gemma4:31b-mtp-vision-bf16

64GB · 256K context window · Text, Image · 3 days ago

gemma4:31b-mtp-vision-bf16

64GB

256K

Text, Image

Readme

Gemma 4 31B

ARCH: GEMMA_V4 // PARAMS: 31B // PRECISION: BF16 // CONTEXT: 256K TOKENS

Hardware & Environment

Designed for local multi-GPU systems and small GPU grids.

Target hardware: AMD Instinct MI50, MI60, MI100 and MI210 series
Recommended memory: 96+ GB HBM / VRAM

Technical Specifications

Model: Gemma 4 31B
Origin 1: Hugging Face google/gemma-4-31B-it
Origin 2: Hugging Face google/gemma-4-31B-it-assistant
Precision: BF16
Vision: Integrated mmproj (archclip) for multimodal input
Acceleration: Multi-Token Prediction (MTP) draft head
Context: Up to 262144 tokens

Quick Start

ollama run home-rag/gemma4:31b-mtp-vision-bf16