Gemma 3 12B — Specifiche tecniche
Compiled by Mustafa Ihsan from the vendor’s published documentation · Last updated
| Sviluppatore | |
|---|---|
| Tipo | LLM (multimodale) |
| Modalità | Testo, immagine → testo |
| Parametri | 12B |
| Finestra contestuale | 128K |
| Licenza | Gemma (open) |
| Pesi aperti | Sì |
| Pubblicato | 2025 |
| Prezzo dell’input | $0.05 /1M |
| Prezzo dell’output | $0.15 /1M |
| Provider API | Google AI Studio, OpenRouter, Ollama |
Esegui localmente
| VRAM (4-bit) | ~8 GB |
|---|---|
| GPU minima | RTX 4070 12 GB |
What is Gemma 3 12B?
Gemma 3 12B is the mid-size member of Google’s open Gemma 3 family: multimodal across text
and images, a 128K context, support for 140+ languages, and a footprint of about 8 GB at
4-bit — which puts it comfortably on an RTX 4070 12GB.
It occupies the position most people actually want from a local model. The 4B is small
enough to feel limited on anything demanding; the 27B needs a 16–24 GB card and pushes past
what a typical developer machine or mid-range gaming GPU offers. The 12B fits the hardware
most people already own while still handling multilingual work and image input properly. That
combination — vision, 140+ languages, 128K context, 8 GB — is the reason it turns up so often
in on-device and privacy-sensitive deployments. If you are choosing a first local model to
build against, this is the one that will run on the widest range of machines without feeling
like a compromise. Size your specific quantisation with the
Calcolatore VRAM before committing to a
card.
Gemma 3 12B pricing: API cost per 1M tokens
| Input (per ogni milione di token) | $0.0500 |
|---|---|
| Output (per ogni milione di token) | $0.150 |
| Rapporto output/input | 3× |
| Combinato (4:1 in:out) | $0.0700 per 1 milione di token |
What Gemma 3 12B 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 | $0.09 |
| Piccolo team | 20 milioni in ingresso / 5 milioni in uscita | $1.75 |
| Produzione | 200 milioni in ingresso / 50 milioni in uscita | $18 |
Calcola i tuoi numeri personalizzati nel Calcolatore dei costi delle API per l'IA.
Cheaper alternatives to Gemma 3 12B
| Modello | Costo combinato ($/1 milione) | Risparmi |
|---|---|---|
| Mistral 7B aperta | $0.0220 | 69% cheaper |
| Llama 3.1 8B aperta | $0.0220 | 69% cheaper |
| Mistral NeMo 12B aperta | $0.0240 | 66% cheaper |
Eseguirlo in autonomia o pagare l’API?
Gemma 3 12B is open-weight, so you can run it yourself. It needs ~8 GB of VRAM at 4-bit (RTX 4070 12GB). 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 12B cost per 1M tokens?
Gemma 3 12B costs $0.0500 per 1M input tokens and $0.150 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.0700 per 1M tokens.
How much does Gemma 3 12B cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $1.75 on Gemma 3 12B. A side project (1M in / 0.25M out) costs roughly $0.09.
What is a cheaper alternative to Gemma 3 12B?
Mistral 7B is the strongest cheaper option in our database at $0.0220 per 1M blended — about 69% less than Gemma 3 12B. It is also open-weight, so self-hosting is an option.
Can I run Gemma 3 12B locally?
Yes. Gemma 3 12B is open-weight and needs about ~8 GB of VRAM at 4-bit quantisation (RTX 4070 12GB).
Why does Gemma 3 12B 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 12B charges 3× 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.