Dedicated model · Available as managed deployment

Request a Gemma-4 26B deployment on your own DGX Spark

A vision-capable open model with a 262,144-token context window — the largest in the AxForge catalogue — validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. An OpenAI-compatible endpoint on your own machine, operated by AxForge in Málaga, Spain.

eu-es-1 · Málaga Available as managed deployment 262,144 ctx · vision Quoted per deployment gemma-4-26b.axforge.ai
Request deploymentTalk to an engineerSign in €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT Hardware rental plus a managed service quoted per deployment — both confirmed in writing before anything is billed.

Why AxForge

Why Gemma-4 26B as a managed deployment

262,144-token contextThe largest context window in the AxForge catalogue — whole documents, long transcripts and large tool outputs in one request.
Text + visionGemma-4 26B accepts image input alongside text: the same endpoint reads screenshots, scans and photos, served under the model name gemma on your own OpenAI-compatible /v1.
EU-hosted, zero prompt retentionA dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) in Málaga, Spain (eu-es-1). Prompts and completions are processed in memory — not logged, not retained, never used to train.

Specifications

What you get

ModelGemma-4 26B — open model, Gemma family
Served model namegemma
Context window262,144 tokens
ModalitiesText + vision — accepts image input
HardwareNVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge
Rental termHour, week, month or year
Hardware pricing€0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT
Managed serviceQuoted per deployment
RegionMálaga, Spain (eu-es-1)

Full details, benchmarks and FAQ on the Gemma-4 26B page. Prices exclude VAT.

How it works

From sign-in to running

1Request deployment — describe your traffic, context needs and rental term.
2You receive the configuration, hardware rental and managed-service price in writing before anything is billed.
3AxForge deploys Gemma-4 26B on a dedicated DGX Spark reserved for you.
4Point your OpenAI SDK at your own endpoint with model gemma — text and image input.
5Adjust the term — hour, week, month or year — as your workload settles.

Request deployment or sign in to start.

FAQ

Gemma-4 26B — common questions

Is Gemma-4 26B on the AxForge serverless API?

Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.

How large is the Gemma-4 26B context window?

262,144 tokens — the largest context window in the AxForge catalogue.

Can Gemma-4 26B process images?

Yes, the model is vision-capable: it accepts image input alongside text.

How fast is it on your hardware?

AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.

What does a dedicated deployment look like?

A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) rented by the hour, week, month or year, running Gemma-4 26B behind an OpenAI-compatible endpoint on your own machine, hosted in the EU with zero prompt retention.

What does it cost?

Two parts: the DGX Spark hardware rental — by the hour, week, month or year, with longer terms earning the lower rate — and the managed service, quoted per deployment. Both are confirmed in writing before anything is billed.

Ready for Gemma-4 26B on your own machine?

Request deployment Sign in Talk to an engineer

Explore

More from AxForge

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms