Sold by: Salient Engineering
Deployed on AWS
Free Trial
A self-hosted, production-ready Bonsai 2 27B model deployed into your AWS environment with a single click. Because everything runs entirely within your private cloud, your data stays secure, isolated, and fully under your control. Best of all, unlimited tokens.
Overview
This is a self-hosted deployment of the Bonsai 2 27B large language model. It runs as a single GPU-powered EC2 instance allowing you to keep your data private and leverage unlimited tokens. Access to the model is via HTTP on port 8080. Once the instance is powered on, the server requires 1 minute to load the LLM before it is ready to serve requests. Highlights of the Bonsai model include:
-
Ternary g128 weights at a true 1.72 bits per weight. This image serves the PQ2_0 packing (2.13 bits per weight, 7.21 GB) together with the optional Q8_0 vision projector.
-
Derived from Qwen3.8-27B: 27.36B parameters, hybrid attention (about 75% linear and 25% full attention), SwiGLU MLP, RoPE, and RMSNorm. The model supports a 262,144-token context. This image uses a 16,384-token context so the weights and cache fit on one 24 GB GPU.
-
Thinking mode is on by default. The model card's thinking-mode sampling is temperature 1.0, top_p 0.95, and top_k 20.
-
The model card reports a 84.78 average across 14 thinking-mode benchmarks, 98.2% of the FP16 reference, with math, coding, and tool-calling scores close to that baseline.
-
Apache 2.0 license. These files need Prism ML's llama.cpp fork; stock llama.cpp and Ollama cannot run them.
Highlights
- Data security, privacy, and confidentiality
- Predictable cost
- Unlimited usage of a dedicated model
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 26.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g5.xlarge Recommended | $0.09 |
Dimensions summary
You pay for this self-hosted model by the hour on a single dimension, the g5.xlarge instance type. Billing is usage-based, so charges accrue for each hour the instance runs in your AWS account. There are no tiers or add-ons to choose between. You pay for the machine that runs the model, not for the number of tokens processed.
Top-of-mind questions for buyers
The g5.xlarge is a single AWS GPU instance type. You pay for each hour that one instance runs in your AWS account. The rate covers the machine that hosts the model. Underlying AWS infrastructure charges for that instance are handled through your AWS bill.
Charges accrue for each hour the g5.xlarge instance actively runs. When you stop the instance, the hourly software fee stops. Stopped instances may still incur AWS storage fees for attached volumes, but the model software meters running time only.
No. You pay for the machine, not for tokens. The hourly instance rate is the only software charge. Whether you process few or many requests, the cost depends on how long the g5.xlarge instance runs, not on processing volume.
www.salientengineering.com
Helpful?
Vendor refund policy
Refunds may be considered on a per-case basis. Please contact us at support@salientengineering.com for inquiries.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
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
Configured for production environments, please allow 1 minute once the instance is powered on for llama.cpp to fully load the LLM. The server is exposed on port 8080.
Test via HTTP with: curl -X POST http://<PUBLIC_IP>:8080/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"Ternary-Bonsai-2-27B","messages":[{"role":"user","content":"In one sentence, explain what a large language model is capable of."}]}'
Additional details
Usage instructions
- Deploy the EC2 instance, configure the Security Group to only allow inbound port 22 and 8080 from your trusted IP address(es)
- After the instance is powered on, allow 1 minute for the server to load the LLM before sending requests.
- Access the Bonsai 2 27B model via the llama.cpp server exposed on port 8080 for HTTP.
Test via HTTP with: curl -X POST http://<PUBLIC_IP>:8080/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"Ternary-Bonsai-2-27B","messages":[{"role":"user","content":"In one sentence, explain what a large language model is capable of."}]}'
Resources
Vendor resources
Support
Vendor support
The Salient Engineering support team can be reached at: support@salientengineering.com
Our team is happy to assist with deployment and configuration issues.
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
A self-hosted, production-ready Qwen 3.8 27B model deployed into your AWS environment with a single click. Because everything runs entirely within your private cloud, your data stays secure, isolated, and fully under your control. Best of all, unlimited tokens.
Initial release of MedGemma 27B Multimodal (google/medgemma-27b-it) on AWS Marketplace. This version delivers Google's most capable open medical AI model, supporting both medical image comprehension and clinical text reasoning including FHIR-based EHR data, across radiology, dermatology, histopathology, and ophthalmology modalities.
IBM Granite Guardian 3.2 5B is a streamlined AI model designed to detect risks in prompts and responses, enhancing safety and efficiency.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.