Gemma 4 31B text-only instruct model with tool-calling and thinking support, quantized to Q3_K_S and optimized for 16 GB VRAM. Supports up to 256K context, with approximately 64K tokens fitting fully within 16 GB VRAM in tested configurations.

tools thinking 31b

ollama run byczech/gemma4-it-16G-Q3_K_S:31b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "byczech/gemma4-it-16G-Q3_K_S:31b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='byczech/gemma4-it-16G-Q3_K_S:31b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'byczech/gemma4-it-16G-Q3_K_S:31b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model byczech/gemma4-it-16G-Q3_K_S:31b

OpenCode ollama launch opencode --model byczech/gemma4-it-16G-Q3_K_S:31b

Hermes Agent ollama launch hermes --model byczech/gemma4-it-16G-Q3_K_S:31b

OpenClaw ollama launch openclaw --model byczech/gemma4-it-16G-Q3_K_S:31b

Models

View all →

Name

1 model

Size / Usage

Context

Input

gemma4-it-16G-Q3_K_S:31b

13GB · 256K context window · Text · 3 weeks ago

gemma4-it-16G-Q3_K_S:31b

13GB

256K

Text

Readme

Context length

The model supports a maximum context window of up to 256K tokens.

On a 16 GB GPU, approximately 64,000 tokens can fit fully within VRAM in tested configurations using a quantized KV cache. Slightly larger context sizes may begin to spill into system RAM, reducing inference performance.

The exact GPU-resident limit may vary depending on:

Ollama version
GPU architecture and driver
Compute backend
KV-cache type
Runtime overhead
Other applications using GPU memory
Parallel requests and loaded models

For a good balance between context size and fully GPU-resident inference on a 16 GB GPU, a context size of around 64K tokens is recommended.