• Pricing
DashboardContact Sales
  • Blogs
  • Discover
  • Docs
  • Community
⌘K

Over 80,000,000 Cloud Servers Launched

Over 80,000,000 Cloud Servers Launched

Cloud ComputeCloud GPUBare MetalFile SystemObject StorageBlock StorageManaged DatabasesCDNServerlessKubernetesContainer RegistryDirect ConnectLoad Balancers
RegionsAdvanced NetworkControl PanelOperating SystemsUpload ISO
Industry CloudOne-Click DeploymentUse Cases
Browse AppsBecome a Vendor
FAQDevelopers / APIsVultr DocsServer StatusBug BountyPromotionsSolution PartnersStart-Up Programs
Our TeamNewsBrand AssetsReferral ProgramCreator ProgramCareersSLALegalVultr Trust CenterContactYour Privacy ChoicesSubprocessorsAccessibility
Contact SalesSign Up

© Vultr 2026 | VULTR is a registered trademark of The Constant Company, LLC.

Terms of ServiceAUPDMCAPrivacy PolicyCookie Policy
Model Library
Arcee AI
InclusionAI Ring 2.6
Poolside
  1. Docs
  2. More
  3. Model Library
  4. InclusionAI Ring 2.6
  5. Ring 2.6 1T

Ring 2.6 1T

Ring-2.6-1T is a trillion-parameter Mixture-of-Experts reasoning model designed for advanced agentic workflows, complex reasoning, and long-horizon task execution. It features an 80-layer architecture with 8,192 hidden size and 64 attention heads, activating 8 experts per token across 256 routed experts and a shared expert. The model incorporates hybrid attention, QK normalization, Multi-Token Prediction, and YaRN context extension for efficient long-context inference. Supporting up to a 256K token context window, it is optimized for enterprise automation, coding, scientific analysis, and multi-step tool-integrated reasoning.

Deploy with NVIDIA B200Contact Sales

About this model

PaperHF Model Card

Ring-2.6-1T is a trillion-parameter Mixture-of-Experts reasoning model designed for advanced agentic workflows, complex reasoning, and long-horizon task execution. It features an 80-layer architecture with 8,192 hidden size and 64 attention heads, activating 8 experts per token across 256 routed experts and a shared expert. The model incorporates hybrid attention, QK normalization, Multi-Token Prediction, and YaRN context extension for efficient long-context inference. Supporting up to a 256K token context window, it is optimized for enterprise automation, coding, scientific analysis, and multi-step tool-integrated reasoning.

Model Type

MoE LLM

Released

May 8, 2026

License: MIT

Parameters

1T

Model ID
inclusionAI/Ring-2.6-1T
Capabilities
Text GenerationInstruction FollowingReasoningMathematical ReasoningCode Generation+4

Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (inclusionAI/Ring-2.6-1T). Released under MIT. Further reading: Paper

Deploy Private Inference Endpoint

Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure

Hardware

B200

1,440 GB

Engine

vLLM
SGLang

Deployment code

INFERENCE COMMAND
Access Restricted

Enter your email to get access to this content

Powered by Vultr AgentBeta

Performance under load

5.8k4.6k3.5k2.3k1.1k0163264128256512Total Tokens / secConcurrent requests
Tokens/s (total)

Benchmarks measured by Vultr on B200 · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.

SS

Shivam Sharma

View Profile
View Profile

NVIDIA HGX B200

Unlock Next-Generation AI Power on Vultr Cloud GPU

Deploy NowContact Sales

NVIDIA HGX B200

Starting Price
$3.50
/GPU/hr
Deploy Now

Tech Talk: Running a Self-Improving AI Agent with Hermes on Vultr

From The Blog

Why CPUs Are the Workhorse of Agentic AI Infrastructure

September 9, 2026

Run Your Own Inference Stack on Vultr with Modelplane

September 3, 2026

Qdrant Builds a 10-Billion-Document Vector Search Benchmark Dataset on Vultr

September 1, 2026

View all posts