Modeldex
Google

gemma-3-4b-pt

SIZE4.3B
Vision
TextImageDownloads130K/mo
TextLikes170

Vision-language model from Google, 4.3B parameters.

Open weightsGemma license502/1044
Drag to turnCard front showing

GoogleTextPromo

gemma-3-4b-pt

Vision-language model from Google, 4.3B parameters.

google/gemma-3-4b-pt
Type
Text
Quality
Not rated yet
Parameters
4.3B (4,300,079,472)
Downloads
130K in the last 30 days
Likes
170
Access to weights
Accept the license on Hugging Face first
On Hugging Face since
Feb 20, 2025
Takes in
Text, Image
Puts out
Text
Access
Open weights
License
Gemma license
Rarity
Promo
Set number
502/1044

License read from the model’s Hugging Face card. Stats from Google’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for gemma-3-4b-pt, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists gemma-3-4b-pt yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

1 provider sells gemma-3-4b-pt through an API. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
Pioneergoogle/gemma-3-4b-pt$0.15$0.1533K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

More from Google

Google

Gemini 4 Argon

CTX1.05M
New
99Quality
Reasoning · Vision · Tools
TextImageAudioVideoPDFInput$2/M
TextOutput$10/M

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

PaidProprietary1037/1044
Google

embeddinggemma-2

SIZE744M
Embedding
TextDownloads170K/mo
–Likes2.7K

Embedding model from Google, 744M parameters.

Open weightsApache 2.01004/1044
Google

Gemini 3.8 Flash

CTX1.05M
93Quality
Reasoning · Vision · Tools
TextImageAudioVideoPDFInput$0.75/M
TextOutput$3.75/M

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

PaidProprietary993/1044
Google

timesfm-3.0-pytorch

SIZE331M
Forecasting
–Downloads1M/mo
–Likes960

Time-series forecasting model from Google, 331M parameters.

Open weightsTimesFM Non Commercial License V1.0987/1044
Google

Gemini 3.7 Flash

CTX1.05M
94Quality
Reasoning · Vision · Tools
TextImageAudioVideoPDFInput$0.75/M
TextOutput$3.75/M

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

PaidProprietary981/1044
Google

Gemini 3.6 Flash

CTX1.05M
86Quality
Reasoning · Vision · Tools
TextImageAudioVideoPDFInput$0.75/M
TextOutput$3.75/M

Fast Gemini model balancing multimodal reasoning, tool use, and cost

PaidProprietary954/1044
Google

Gemini 3.5 Flash Lite

CTX1.05M
68Quality
Reasoning · Vision · Tools
TextImageAudioVideoPDFInput$0.30/M
TextOutput$2.50/M

Fast Gemini model balancing multimodal reasoning, tool use, and cost

PaidProprietary953/1044
Google

Nano Banana 2 Lite

CTX66K
83Quality
Image generation
TextImageInput$0.25/M
TextImageOutput$30/M

Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing

PaidProprietary938/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot