gpuos

Vision · Free plan

Run Gemma 3 4B on your own GPU

Gemma 3 4B is a vision catalog model (4B dense) managed with Ollama. Catalog memory is estimated at 6 GB with Q4_K_M for a short context (4–8K tokens). Validate output quality and memory use with your workload on your hardware.

Deploy the catalog Ollama tag on your machine and verify the pulled model's quantization. Once deployed, gpuos serves it as gemma-3-4b through the hosted gpuos gateway, with API keys, optional token quotas and usage metering. Request and response payloads pass through that gateway.

Parameters
4B dense
Quantization
Q4_K_M
Est. VRAM (4–8K ctx)
≈ 6 GB
Catalog context
128K tokens
License
Gemma Terms of Use
Engine
Ollama
Ollama tag
gemma3:4b
API
/v1/chat/completions

Gemma's terms add use restrictions. Review them before commercial use.

Compare GPU memory for Gemma 3 4B

Catalog estimate at Q4_K_M, not a measured benchmark. Chat estimates assume a short context; embedding memory depends on input and batch size. The comparison includes a 5% screening margin; it does not establish runtime performance. More in how much VRAM an LLM needs.

Check this estimate against your GPU with the VRAM calculator

Call Gemma 3 4B with the OpenAI SDK

Use the supported chat completions endpoint with your gpuos base URL, API key and deployed model id. Validate any model-specific features your app needs. Setup for LangChain, Continue, Open WebUI and more is in integrations.

Python
from openai import OpenAI

client = OpenAI(base_url="https://gpuos.si/v1", api_key="gpuos_key_…")
stream = client.chat.completions.create(
    model="gemma-3-4b",
    messages=[{"role": "user", "content": "Summarize our refund policy."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
Node.js
import OpenAI from "openai"

const client = new OpenAI({ baseURL: "https://gpuos.si/v1", apiKey: process.env.GPUOS_API_KEY })
const reply = await client.chat.completions.create({
  model: "gemma-3-4b",
  messages: [{ role: "user", content: "Summarize our refund policy." }],
})
console.log(reply.choices[0].message.content)
curl
curl https://gpuos.si/v1/chat/completions \
  -H "Authorization: Bearer $GPUOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemma-3-4b", "messages": [{"role": "user", "content": "Hello"}]}'

Questions

How much VRAM does Gemma 3 4B need?
The catalog estimate is 6 GB at Q4_K_M for a short context (4–8K tokens). The RTX 4060 Ti 8 GB clears this estimate with screening headroom in the comparison list. This is a planning estimate, not a tested hardware requirement. Validate context length, batch size and concurrent requests on your node.
Can I use Gemma 3 4B commercially?
Gemma 3 4B is released under the Gemma Terms of Use. Gemma's terms add use restrictions. Review them before commercial use.
Is Gemma 3 4B compatible with the OpenAI API?
Through gpuos, Gemma 3 4B uses the supported /v1/chat/completions endpoint with the model id "gemma-3-4b". Configure your OpenAI-compatible client with the gpuos base URL and API key. Check model-specific features and any other API operations your app needs before switching.
Which gpuos plan includes Gemma 3 4B?
Gemma 3 4B is in the base catalog, available on the free Community plan (1 node, 1 GPU).

Related models

Plan your Gemma 3 4B deployment with gpuOS

Create a free workspace and follow the quickstart to connect a node. Start with a Community model, or upgrade inside your workspace for the full catalog.

Start freeRead the quickstart