Gemma 3 4B — Especificações
| Desenvolvedor | |
|---|---|
| Tipo | LLM (multimodal) |
| Modalidade | Texto, Imagem → Texto |
| Parâmetros | 4B |
| Janela de contexto | 128K |
| Saída máxima | — |
| Licença | Gemma (aberta) |
| Pesos abertos | Sim |
| Lançado | 2025 |
| Preço da entrada | US$ 0,05 / 1 milhão |
| Preço da saída | US$ 0,10 por 1 milhão |
| Provedores de API | Google AI Studio, Ollama |
Execute-o localmente
| VRAM (4 bits) | ~3 GB |
|---|---|
| GPU mínima | Qualquer GPU com 6 GB ou mais |
What is Gemma 3 4B?
Gemma 3 4B is the compact end of Google’s open Gemma 3 family: multimodal text and image
input, a 128K context, and roughly 3 GB of VRAM at 4-bit — small enough for almost any modern
GPU, and for a good deal of hardware that is not a GPU at all.
What is unusual here is the context window. A 4B model with 128K context is not the normal
trade-off; small models historically shipped with small windows, which limited them to short
prompts and made them useless for document work. Gemma 3 4B can hold a substantial document
in memory on a 6 GB card, which opens up edge and on-device use cases — local document
search, offline assistants, in-browser or in-app inference — that previously required sending
data to a server. Do not expect it to reason like a frontier model; expect it to be the
model that makes a privacy-preserving feature feasible at all. At $0.05 in / $0.10 out per
million tokens the hosted option is close to free, so self-hosting here is about data
residency and latency, not cost.
Gemma 3 4B pricing: API cost per 1M tokens
| Entrada (por 1 milhão de tokens) | $0.0500 |
|---|---|
| Saída (por 1 milhão de tokens) | $0.100 |
| Output/input ratio | 2× |
| Blended (4:1 in:out) | $0.0600 per 1M tokens |
What Gemma 3 4B costs per month
Real monthly spend at a 4:1 input-to-output mix — the ratio a typical chat or RAG workload actually produces.
| Carga de trabalho | Tokens/mês | Cost / month |
|---|---|---|
| Projeto paralelo | 1 milhão de tokens de entrada / 0,25 milhão de tokens de saída | $0.08 |
| Equipe pequena | 20 milhões de tokens de entrada / 5 milhões de tokens de saída | $1.50 |
| Produção | 200 milhões de tokens de entrada / 50 milhões de tokens de saída | $15 |
Run your own numbers in the Calculadora de custos de API de IA.
Cheaper alternatives to Gemma 3 4B
| Modelo | Custo médio ponderado por US$ 1 milhão | You save |
|---|---|---|
| Mistral 7B aberta | $0.0220 | 63% cheaper |
| Llama 3.1 8B aberta | $0.0220 | 63% cheaper |
| Mistral NeMo 12B aberta | $0.0240 | 60% cheaper |
Self-host or pay the API?
Gemma 3 4B is open-weight, so you can run it yourself. It needs ~3 GB of VRAM at 4-bit (Any 6GB+ GPU). Self-hosting only beats the API once your volume is high enough to keep that hardware busy — the calculadora de autohospedagem versus API works out the break-even point for your token volume.
Perguntas frequentes
How much does Gemma 3 4B cost per 1M tokens?
Gemma 3 4B costs $0.0500 per 1M input tokens and $0.100 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.0600 per 1M tokens.
How much does Gemma 3 4B cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $1.50 on Gemma 3 4B. A side project (1M in / 0.25M out) costs roughly $0.08.
What is a cheaper alternative to Gemma 3 4B?
Mistral 7B is the strongest cheaper option in our database at $0.0220 per 1M blended — about 63% less than Gemma 3 4B. It is also open-weight, so self-hosting is an option.
Can I run Gemma 3 4B locally?
Yes. Gemma 3 4B is open-weight and needs about ~3 GB of VRAM at 4-bit quantisation (Any 6GB+ GPU).
Why does Gemma 3 4B charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. Gemma 3 4B charges 2× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
Prices are the published list rates for the model's primary API and are reviewed as providers change them. Volume, batch and cached-input discounts are not included. Compare every model side by side in the Banco de dados de modelos de IA ou o Ranking de LLMs.
