Gemma 3 4B

A compact 4B model in Google's open-weight Gemma 3 family, built for local and edge deployments.

Params: 4.3B
Context: 128K tokens
Max output: 128K
Cutoff: Aug 2024
Released: Mar 2025
License: Gemma Terms of Use

Visit Google Cloud Compare vs other LLMs →

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Gemma 3 4B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Gemma 3 4B, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Google Cloud Creator	Open weights, no hosted price			Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Gemma 3 4B needs about 5 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 1× GTX 1660 Super at about $29 a month.

Fits on 1

What it costs to self-host Gemma 3 4B at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 128K context)	Cost /mo
4-bit INT4 / FP4	5 GB7 GB	1× GTX 1660 Super	$29$50
8-bit FP8 / INT8	7 GB9 GB	1× RTX 2070	$50$58
16-bit FP16 / BF16	11 GB13 GB	1× RTX 4060 Ti	$94$94

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Thunder Compute

RTX A6000 from $0.35, A100 from $1.09, per GPU per hour

Billed per minute, no commitment, no minimums

One click into VS Code or Cursor, no SSH setup

See live pricing

Capabilities

What Gemma 3 4B accepts and can do, as published by Google Cloud.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Function calling Connect to external tools, APIs, and systems.

Common questions

What is Gemma 3 4B good for?

Local and edge deployments taking text and images. Open weights under the Gemma Terms of Use, small enough for a single consumer GPU.

When is Gemma 3 4B not a good fit?

Video or audio input, and structured output. The Gemma Terms of Use are a custom license rather than Apache 2.0, and the Gemma 4 family knows more recent events.

What is the cheapest way to run Gemma 3 4B?

No provider we track hosts it; self-hosting on the cheapest rental that fits (1x GTX 1660 Super, $0.04 per hour) costs about $29 a month.

Can I self-host Gemma 3 4B?

Yes. The weights are released under the Gemma Terms of Use. At 4-bit it needs about 5 GB of GPU memory, which starts at roughly $29 a month on the cheapest rental that fits.