Model garden Router · op aanvraag Dedicated · beschikbaar

gemma 4 31B it

Dit model draait als eigen dedicated GPU-deployment, direct te starten via de wizard. Data blijft in Europa.

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 vari...

google/gemma-4-31B-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
31B
Parameters
262K
Contextvenster
80GB
Minimale VRAM
POST /api/v1/chat/completions Op aanvraag

Specificaties

Parameters 31B
Contextvenster 262,144 tokens
Minimale VRAM 80 GB
Architectuur Gemma4ForConditionalGeneration (vLLM)
Licentie apache-2.0
Modaliteit text+image->text
Uitgebracht March 2026
Uitgever google ↗

Prijzen

Gedeelde router · per token
Op aanvraag
Niet beschikbaar op de gedeelde router. Prijs op aanvraag als dedicated GPU-deployment.
Dedicated GPU · per uur
vanaf €1,08 per uur
Eigen vLLM-instance op Europese cloud (80 GB VRAM), per uur afgerekend.

Gedeelde EU-router, pay-per-token, scale-to-zero. Dedicated GPU-deployments worden per uur afgerekend, zie prijzen.

✓ Werkend geverifieerd op 26-07-2026, respons in 3171 ms op onze EU-infrastructuur.

Bench-index

Bench is onze kwaliteitsindex voor elk model, 0 tot 100. Hij steunt op openbare metingen (Epoch AI met zo’n 40 benchmarks, LiveBench, LMArena en meer) en wordt elke ochtend ververst. Waar niemand meet, staat een schatting met bandbreedte.

66,2 / 100 · Gemeten

Gemeten door Epoch AI over 7 benchmarks, met bandbreedte.

Bandbreedte 62,9 tot 69,7 · Plek 102 van 270 bij Epoch AI

Bronnen: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Dagelijks bijgewerkt, laatst op 24-10-2026

LiveBench · 61,6
Redeneren 59,4
Code 60,3
Agentisch coderen 40,0
Wiskunde 73,9
Data-analyse 58,8
Taal 71,3
Instructies volgen 67,6
Alle benchmarks (7)
OTIS Mock AIME 2024-2025 73,3
DTBench 71,1
GPQA diamond 70,5
WeirdML 52,3
LMCA 46,2
Surface Evolver Bench 30,6
SimpleQA Verified 10,4
LiveBench · Alle taken
Redeneren
theory of mind 51,9
zebra puzzle 29,8
spatial 92,0
logic with navigation 64,0
Code
code generation 62,0
code completion 58,7
Agentisch coderen
javascript 20,0
typescript 35,0
python 65,0
Wiskunde
AMPS Hard 100,0
integrals with game 26,3
math comp 87,3
olympiad 82,2
Data-analyse
consecutive events 29,9
tablejoin 46,4
tablereformat 100,0
Taal
connections 92,5
plot unscrambling 47,5
typos 74,0
Instructies volgen
paraphrase 69,5
simplify 61,3
story generation 71,7
summarize 67,9

Direct aanroepen

Drop-in vervanger voor OpenAI: wijzig alleen de base-URL en de API-key. Ook het Anthropic-formaat (/v1/messages) wordt ondersteund.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31B-it",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Veelgestelde vragen

Kan ik gemma 4 31B it in de EU draaien?

Ja. HostYourAI draait gemma 4 31B it op GPU's in Europese datacenters via vLLM. Prompts en outputs verlaten de EU niet en er is geen Amerikaanse cloudprovider in de keten.

Is gemma 4 31B it hosten AVG/GDPR-compliant?

Ja. Alle verwerking vindt plaats binnen de EU, er is een verwerkersovereenkomst (DPA) beschikbaar en de subprocessor-lijst is openbaar. Open-source gewichten betekenen ook: geen training op jouw data.

Wat kost gemma 4 31B it?

gemma 4 31B it is beschikbaar op aanvraag: via de gedeelde EU-router na kort overleg, of als eigen dedicated GPU-deployment per uur. Vertel ons je use case, dan zetten we het voor je klaar.

Is de API compatibel met OpenAI?

Ja. Je gebruikt de standaard OpenAI-SDK's met een aangepaste base-URL (https://hostyourai.com/api/v1). Ook de Anthropic Messages API wordt ondersteund als drop-in.

Andere modellen van 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 Bekijk 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 Bekijk 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 Bekijk 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 Bekijk 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 Bekijk 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 Bekijk model →

Probeer gemma 4 31B it gratis

Account aanmaken duurt een minuut. Test gemma 4 31B it direct in de playground.

Start gratis