HostYourAI
Product
EU RouterDecision models like JevHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Earn with your GPU
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.3Kimi K2.7 CodeQwen3.5 397BLlama 3.3 70BMistralMiniMax M3All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAICompare costs
Resources
DocumentationSavings checkGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalogNewsSecurityFAQ
Pricing News
NL EN DE FR ES
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

gemma 3 4b it

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

gemma 3 4b it is an multimodal language model from Google with 4.3B parameters, hosted on EU GPUs via an OpenAI-compatible API.

Start for free ← All models
google/gemma-3-4b-it vLLM ready
text+image->text · google · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
4.3B
Parameters
—
Context window
16GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 4.3B
Minimum VRAM 16 GB
Architecture Gemma3ForConditionalGeneration (vLLM)
License gemma
Modality text+image->text
Released February 2025
Publisher google ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Dedicated GPU · per hour
from €1,08 per hour
Your own vLLM instance on European cloud (16 GB VRAM), billed hourly.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

✓ Verified working on 31-07-2026, responded in 869 ms on our EU infrastructure.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

32.3 / 100 · Measured

Measured by Epoch AI across 4 benchmarks, with a range.

Range 9.2 to 42.0 · Rank 213 of 270 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 24-10-2026

LiveBench · 30.1
Reasoning 19.8
Coding 11.7
Mathematics 31.3
Data analysis 39.3
Language 15.1
Instruction following 63.6
Every benchmark (4)
DTBench 18.2
OTIS Mock AIME 2024-2025 7.4
LMCA 3.3
GPQA diamond 0.0
LiveBench · All tasks
Reasoning
web of lies v3 26.3
zebra puzzle 11.0
spatial 22.0
Coding
LCB generation 12.0
coding completion 11.4
Mathematics
AMPS Hard 57.0
math comp 19.8
olympiad 17.2
Data analysis
cta 44.0
tablejoin 5.9
tablereformat 68.0
Language
connections 10.2
plot unscrambling 11.0
typos 24.0
Instruction following
paraphrase 65.8
simplify 70.3
story generation 60.7
summarize 57.6

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3-4b-it",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run gemma 3 4b it in the EU?

Yes. HostYourAI runs gemma 3 4b it on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting gemma 3 4b it GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does gemma 3 4b it cost?

gemma 3 4b it is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per hour. Tell us your use case and we will set it up for you.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from Google

embeddinggemma 2

EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders.

0.7B 262K context View model →
diffusiongemma 26B A4B it

DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.

26B 262K context View model →
gemma 4 31B it qat w4a16 ct

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoints are available: Unquantized QAT checkpoints (Q40): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. GGUF (Q40): Ready-to-deploy formats for broad ecosystem compatibility. Availabl

33B 262K context View model →
gemma 4 26B A4B it qat q4 0 unquantized

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoints are available: Unquantized QAT checkpoints (Q40): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. GGUF (Q40): Ready-to-deploy formats for broad ecosystem compatibility. Availabl

26B 262K context View model →
gemma 4 31B it qat q4 0 unquantized

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoints are available: Unquantized QAT checkpoints (Q40): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. GGUF (Q40): Ready-to-deploy formats for broad ecosystem compatibility. Availabl

31B 262K context View model →
gemma 4 31B

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

33B 262K context View model →

Try gemma 3 4b it for free

Creating an account takes a minute. Test gemma 3 4b it straight away in the playground.

Start for free