Gemma 4 E4B

A compact 4.5B dense model in Google's Gemma 4 family with native speech recognition and translation. Apache 2.0 license.

Params: 8B
Context: 128K tokens
Cutoff: Jan 2025
Released: Apr 2026
License: Apache 2.0

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 4 E4B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Gemma 4 E4B, 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 4 E4B needs about 7 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 1× RTX 2070 at about $50 a month.

Fits on 1 Single node ≤ 8

What it costs to self-host Gemma 4 E4B 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	7 GB8 GB	1× RTX 2070	$50$58
8-bit FP8 / INT8	11 GB11 GB	1× RTX 3060	$58$94
16-bit FP16 / BF16	19 GB20 GB	2× RTX 3060	$115$115

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.

GPUhub

Fully Dedicated GPU Servers

No Virtualization. No Shared GPUs

Stable Performance for AI Training & Inference

Full Control for Production Workloads

Learn more

Capabilities

What Gemma 4 E4B accepts and can do, as published by Google Cloud.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Audio Accepts audio as input.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.

Common questions

What is Gemma 4 E4B good for?

Compact local deployments with native speech recognition and translation, taking text, images and audio. Apache 2.0 weights, small enough for a single consumer GPU.

When is Gemma 4 E4B not a good fit?

Video input, and hosted tools like web search or code execution. No maximum output is published.

What is the cheapest way to run Gemma 4 E4B?

No provider we track hosts it; self-hosting on the cheapest rental that fits (1x RTX 2070, $0.07 per hour) costs about $50 a month.

Can I self-host Gemma 4 E4B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 7 GB of GPU memory, which starts at roughly $50 a month on the cheapest rental that fits.