• 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
Granite 4.2 30BGranite 4.2 8BGranite 4.2 3B
Poolside
  1. Docs
  2. More
  3. Model Library
  4. IBM Granite 4.2
  5. Granite 4.2 8B

Granite 4.2 8B

Granite 4.2 8B is a small-size reasoning model designed for coding, mathematics, tool calling, agentic workflows, and multilingual dialogue. It features 8B parameters with a 40-layer dense transformer using 4,096 hidden size, 32 attention heads, and 8 KV heads. The architecture employs Grouped Query Attention, RoPE with a 10M theta, and a 12,800-dimensional SwiGLU feed-forward network, with native reasoning and flexible thinking modes for balancing quality and latency. Supporting 128K native context with extension to 512K, it is optimized for efficient long-context reasoning and enterprise applications.

Deploy with NVIDIA B200Contact Sales

About this model

BlogHF Model Card

Granite 4.2 8B is a small-size reasoning model designed for coding, mathematics, tool calling, agentic workflows, and multilingual dialogue. It features 8B parameters with a 40-layer dense transformer using 4,096 hidden size, 32 attention heads, and 8 KV heads. The architecture employs Grouped Query Attention, RoPE with a 10M theta, and a 12,800-dimensional SwiGLU feed-forward network, with native reasoning and flexible thinking modes for balancing quality and latency. Supporting 128K native context with extension to 512K, it is optimized for efficient long-context reasoning and enterprise applications.

Model Type

Dense LLM

Released

August 25, 2026

License: Apache 2.0

Parameters

8B

Model ID
ibm-granite/granite-4.2-8b
Capabilities
Text GenerationInstruction FollowingReasoningMathematical ReasoningCode Generation+4

Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (ibm-granite/granite-4.2-8b). Released under Apache 2.0. Further reading: Blog

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

Ensure that granite_thinking_parser.py is present inside mapped local model directory prior to initialization to satisfy the container's plugin path requirement.

Performance under load

115k92k69k46k23k011664128256512Total 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

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

Vultr Named a “Strong Performer” in Forrester Wave™: Public Cloud Platforms, Q3 2026

August 31, 2026

View all posts