Gemma 3 27B Instruct

The largest model in Google's open-weight Gemma 3 family at 27B parameters, multilingual and sized for a single GPU.

Params: 27.4B
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 price

Cheapest via Lyceum · per 1M tokens

USD

Input: $0.10 /1M
Output: $0.30 /1M
Hosted by: 3 providers

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 27B Instruct, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Gemma 3 27B Instruct, 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
Lyceum Cheapest	$0.10	$0.30	$1.60	Visit website
Novita	$0.12	$0.20	$1.60	Visit website
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 27B Instruct needs about 20 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 2× RTX 3060 at about $101 a month.

That costs the same as roughly 756M tokens a month on Lyceum's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Gemma 3 27B Instruct 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	Break-even vs API
4-bit INT4 / FP4	20 GB22 GB	2× RTX 3060	$101$173	756M tokens /mo1B tokens /mo
8-bit FP8 / INT8	32 GB40 GB	4× RTX 3060	$202$202	2B tokens /mo2B tokens /mo
16-bit FP16 / BF16	59 GB67 GB	8× RTX 3060	$403$403	3B tokens /mo3B tokens /mo

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. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Gemma 3 27B Instruct by blended rate, each at its own cheapest provider.

Models priced nearest Gemma 3 27B Instruct per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Gemma 3 27B Instruct
Ministral 3 3B Mistral	$0.10	$0.10	$0.10	256K		−25%
GLM-5.3-Flash Z.AI	$0.1083	$0.08	$0.25	1M		−19%
GPT-5 Nano OpenAI	$0.1083	$0.05	$0.40	400K	May 2024	−19%
Qwen3.5-35B-A3B Alibaba Cloud	$0.1267	$0.06	$0.46	262K		−5%
Qwen3.6-35B-A3B Alibaba Cloud	$0.1283	$0.07	$0.42	262K		−4%
Gemma 3 27B Instruct This model Google Cloud	$0.1333	$0.10	$0.30	128K	Aug 2024
Gemma 4 26B A4B Google Cloud	$0.1333	$0.10	$0.30	256K	Jan 2025	0%
Qwen3-32B FP8 Alibaba Cloud	$0.1333	$0.10	$0.30	33K		0%
Gemini 2.5 Flash-Lite Google Cloud	$0.15	$0.10	$0.40	1M	Jan 2025	+13%
GPT-4.1 Nano OpenAI	$0.15	$0.10	$0.40	1M	Jun 2024	+13%
Ministral 3 8B Mistral	$0.15	$0.15	$0.15	256K		+13%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Packet·ai

B200 @ $3.75/h on demand

No contract, no spot interrupts, no cluster minimums

Full root SSH, web dashboard, CI/CD ready

Reserve Now

Capabilities

What Gemma 3 27B Instruct 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 27B Instruct good for?

Multilingual text generation and image understanding, at the heavy end of the Gemma 3 family. Open weights under the Gemma Terms of Use, still on a single consumer GPU.

When is Gemma 3 27B Instruct 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 27B Instruct?

Hosted, unless you push serious volume. Lyceum charges $0.10 in / $0.30 out per 1M tokens. The cheapest rental that fits is 2x RTX 3060 at $101 a month, which costs the same as about 756M tokens a month on that API.

Can I self-host Gemma 3 27B Instruct?

Yes. The weights are released under the Gemma Terms of Use. At 4-bit it needs about 20 GB of GPU memory, which starts at roughly $101 a month on the cheapest rental that fits.