• Pricing
DashboardContact Sales
  • Blogs
  • Discover
  • Docs
  • Community
  • AgentBeta
⌘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
Cohere Command A PlusCohere North Mini Code
Tiny Aya WaterTiny Aya GlobalTiny Aya FireTiny Aya EarthTiny Aya Base
PoolsideReflection AI
  1. Docs
  2. More
  3. Model Library
  4. Cohere Tiny Aya
  5. Tiny Aya Fire

Tiny Aya Fire

Tiny Aya Fire is a 3.35B-parameter multilingual language model optimized for South Asian languages. It uses a 36-layer transformer with 2,048 hidden size, 16 attention heads, and 4 KV heads. The architecture interleaves sliding window attention (4,096 window) with periodic global attention layers for efficient long-range interaction. It supports around 8K context length and uses RoPE for positional encoding. Trained across 70+ languages, it is designed for strong regional performance while remaining efficient for local deployment and downstream adaptation.

Deploy with AMD MI325XContact Sales

About this model

PaperBlogHF Model Card

Tiny Aya Fire is a 3.35B-parameter multilingual language model optimized for South Asian languages. It uses a 36-layer transformer with 2,048 hidden size, 16 attention heads, and 4 KV heads. The architecture interleaves sliding window attention (4,096 window) with periodic global attention layers for efficient long-range interaction. It supports around 8K context length and uses RoPE for positional encoding. Trained across 70+ languages, it is designed for strong regional performance while remaining efficient for local deployment and downstream adaptation.

Model Type

Dense LLM

Released

February 17, 2026

License: CC-BY-NC-4.0

Parameters

3B

Model ID
CohereLabs/tiny-aya-fire
Capabilities
Text GenerationInstruction FollowingText ClassificationMultilingual

Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (CohereLabs/tiny-aya-fire). Released under CC-BY-NC-4.0. Further reading: Paper · Blog

Deploy Private Inference Endpoint

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

Hardware

MI325X

2,048 GB

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

57k46k34k23k11k011664128256512Total Tokens / secConcurrent requests
Tokens/s (total)

Benchmarks measured by Vultr on MI325X · 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

AMD Instinct MI325X

Unlock Next-Generation AI Power on Vultr Cloud GPU

Deploy NowContact Sales

AMD Instinct MI325X

Starting Price
$2.00
/GPU/hr
Deploy Now

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

From The Blog

Optimize CPU Spend to Accelerate AI: A FinOps Approach to Infrastructure Investment

November 18, 2026

KubeCon + CloudNativeCon 2026: Growing Our Open Source Community in Salt Lake City

November 16, 2026

Optimizing Agentic AI Workflows Through Full-Stack Infrastructure

November 13, 2026

View all posts