Gemma 3 4B — Specifiche
Compiled by Mustafa Ihsan from the vendor’s published documentation · Last updated
| Sviluppatore | |
|---|---|
| Tipo | LLM (multimodale) |
| Modalità | Testo, immagine → testo |
| Parametri | 4 miliardi |
| Finestra contestuale | 128K |
| Licenza | Gemma (open) |
| Pesi aperti | Sì |
| Pubblicato | 2025 |
| Prezzo dell’input | $0.05 /1M |
| Prezzo dell’output | $0.1 /1M |
| Provider API | Google AI Studio, Ollama |
Esegui localmente
| VRAM (4-bit) | ~3 GB |
|---|---|
| GPU minima | Qualsiasi GPU da 6 GB o superiore |
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
| Input (per ogni milione di token) | $0.0500 |
|---|---|
| Output (per ogni milione di token) | $0.100 |
| Rapporto output/input | 2× |
| Combinato (4:1 in:out) | $0.0600 per 1 milione di token |
What Gemma 3 4B costs per month
Spesa mensile reale con un mix input-to-output 4:1 — il rapporto effettivamente prodotto da un tipico carico di lavoro basato su chat o RAG.
| Carico di lavoro | Token/mese | Costo/mese |
|---|---|---|
| Progetto secondario | 1 milione in ingresso / 0,25 milioni in uscita | $0.08 |
| Piccolo team | 20 milioni in ingresso / 5 milioni in uscita | $1.50 |
| Produzione | 200 milioni in ingresso / 50 milioni in uscita | $15 |
Calcola i tuoi numeri personalizzati nel Calcolatore dei costi delle API per l'IA.
Cheaper alternatives to Gemma 3 4B
| Modello | Costo combinato ($/1 milione) | Risparmi |
|---|---|---|
| Mistral 7B aperta | $0.0220 | 63% più economico |
| Llama 3.1 8B aperta | $0.0220 | 63% più economico |
| Mistral NeMo 12B aperta | $0.0240 | 60% cheaper |
Eseguirlo in autonomia o pagare l’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 calcolatore self-hosting vs API calcola il punto di pareggio in base al tuo volume di token.
Domande frequenti
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.
I prezzi indicati sono le tariffe ufficiali pubblicate per l'API principale del modello e vengono aggiornati man mano che i fornitori li modificano. Sconti per volumi elevati, elaborazione batch e input memorizzati nella cache non sono inclusi. Confronta tutti i modelli fianco a fianco nel Database di modelli IA o il Classifica LLM.