Overview
This is a self-hosted deployment of the Gemma 4 26B A4B large language model. It runs as a single GPU-powered EC2 instance allowing you to keep your data private and leverage unlimited tokens. Access is over HTTPS on port 443 with a per-instance API key; Ollama itself listens only on localhost. GPU instance types need EC2 quota for "Running On-Demand G and VT instances" (L-DB2E81BA), which new AWS accounts often have set to 0. The model is preloaded into GPU memory on boot, so the first prompt does not wait for a cold load. Once the instance is powered on, the model is ready in about 8 minutes. Highlights of the Gemma 4 26B model include:
-
Advanced Reasoning - Every model in the family is built for strong reasoning performance, with adjustable thinking modes to fit different use cases.
-
Expanded Multimodal Support - Handles text and images with flexible aspect ratio and resolution support across all models, plus native video and audio capabilities on the E2B and E4B models.
-
Flexible and Efficient Architectures - Includes both Dense and Mixture-of-Experts (MoE) model variants in multiple sizes, enabling scalable deployment options.
-
Built for On-Device Performance - Smaller models are optimized for efficient local use on laptops, smartphones, and other mobile devices.
-
Larger Context Windows - Small models support up to 128K context, while medium models extend this to 256K for more complex tasks.
-
Stronger Coding & Agentic Performance - Delivers significant gains on coding benchmarks and includes native function-calling support for powerful autonomous agent workflows.
-
Native System Prompting - Gemma 4 adds built-in system role support, allowing for more structured, guided, and controllable interactions.
Highlights
- Data security, privacy, and confidentiality
- Predictable cost
- Unlimited usage of a dedicated model
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
|---|---|
g6.xlarge Recommended | $0.09 |
g5.2xlarge | $0.09 |
g6e.2xlarge | $0.09 |
g5.xlarge | $0.09 |
g6e.xlarge | $0.09 |
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
Refunds may be considered on a per-case basis. Please contact us at support at salientengineering.com for inquiries.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Ubuntu security updates through 2026-11-17. The AWS kernel is 7.0.0-1017. On GPU images the matching NVIDIA open kernel module was installed in the same update, then linux and NVIDIA packages were held again so a later unattended upgrade cannot split the driver from the kernel. Application behavior is unchanged.
Additional details
Usage instructions
Before you launch: GPU instance types need the EC2 quota "Running On-Demand G and VT instances" (quota code L-DB2E81BA) in your Region to be at least the instance's vCPU count (g6.xlarge = 4 vCPUs). New AWS accounts often have 0, and the launch then fails. Check it or request an increase at https://console.aws.amazon.com/servicequotas/home/services/ec2/quotas/L-DB2E81BA before you subscribe.
- Launch on g6.xlarge or another listed type. In the Security Group, allow inbound TCP 443 from the addresses that will call the API, and TCP 22 only if you need SSH.
- Wait about 8 minutes. EC2 console > your instance > Actions > Monitor and troubleshoot > Get system log shows "Salient LLM appliance: READY" with the endpoint, API key and examples. Status at any time: curl -k https://<PUBLIC_IP>/healthz
- Call the API with the key from the system log (or /home/ubuntu/salient-api-key over SSH): curl -k https://<PUBLIC_IP>/api/tags -H "Authorization: Bearer <API_KEY>" curl -k https://<PUBLIC_IP>/v1/chat/completions -H "Authorization: Bearer <API_KEY>" -H "Content-Type: application/json" -d '{"model":"gemma4:26b","messages":[{"role":"user","content":"Hello"}]}'
- The TLS certificate is self-signed: use -k, or pin the SHA-256 fingerprint printed in the system log. For a trusted certificate, set SALIENT_DOMAIN and SALIENT_LETSENCRYPT_EMAIL in user data (needs a DNS record and TCP 80 open), or run sudo salient-enable-letsencrypt DOMAIN EMAIL. Settings (your own API key, allowed browser origins, context length) go in /etc/salient/salient.conf or EC2 user data, for example SALIENT_ALLOWED_ORIGINS=https://app.example.com .
Resources
Vendor resources
Support
Vendor support
The Salient Engineering support team can be reached at: support@salientengineering.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products

