Model library / Chat / reasoning

Gemma 3 27B: GPU requirements and hosting

Google's instruction-tuned Gemma checkpoint supports text and image understanding upstream. The current catalog profile is text chat; image serving needs separate validation.

Sources reviewed 2026-09-30 · B3IQ engineering

Runtime profiles and requirements

An upstream multimodal capability does not establish that the catalog profile exposes it. The memory figures below apply only to the stated catalog profile.

ollama · gemma3-27b

Catalog GPU threshold: 24 GB
Configured context: 8,192 tokens
Catalog system RAM: 48 GB

Runtime: ollama
Artifact identifier: gemma3:27b
Precision: Not pinned in catalog
Configured concurrency: 1 request(s)
Profile inputs / outputs: text → text
Deployed artifact revision: Not verified

Catalog thresholds are configuration guidance, not measured peak memory. A positive GPU requirement is not recorded for every profile; unspecified is not zero. Context, concurrency and runtime overhead can increase memory use. Configured context is a profile setting, not the upstream maximum. Concurrency is configuration, not a load-test result.

Weight-only arithmetic and a planning estimate

Using the catalog's approximate 27B total parameters, 16-bit weights alone occupy about 54 GB (parameters × 2 bytes). The shared sizing helper rounds a 20% planning reserve to 65 GB.

This arithmetic does not describe the selected quantized artifact. It excludes a workload-specific KV-cache calculation and cannot guarantee fit at the configured context or concurrency. A mixture-of-experts model still stores its full weights.

See the assumptions →

Plan the machine.

Memory-based machine candidates depend on the current visible store configurations. Confirm runtime compatibility, GPU count, interconnect and workload before purchase. Pricing and availability are shown on the machine page.

Explore machines

Before deployment

Test the workload you need.

For a text workload, compare it with similarly sized text models. For images, test the exact image processor, resolution and runtime path you intend to use.

These are catalog profiles and planning figures. No B3IQ performance measurement or live capacity is claimed. Confirm the artifact, runtime, workload and machine before deployment.

Evidence available

Upstream identity / license: Source reviewed
Runtime settings: Catalog configuration
Memory fit: Guidance; not a measured peak
B3IQ performance: No published benchmark
Installation / live capacity: Confirm for your machine

Read our evidence standard →

Source and access.

Upstream checkpoint: google/gemma-3-27b-it ↗
Upstream license metadata: Gemma Terms of Use ↗
Access: Upstream repository requires access approval or acceptance of terms.
Reviewed source revision: 005ad3404e59d6023443cb575daa05336842228a ↗

The reviewed revision identifies the source used for this guide. It is not a claim that this revision is installed on a B3IQ machine. Review the publisher's current license and acceptable-use terms for your application.