Inkling 2 Mini

Inkling 2 Mini

Thinking Machines Lab
Inkling 2 Mini Nemotron 3 Ultra

Related Products

  • LTX
    4.4 out of 5 stars 182 Ratings
    Visit Website for LTX
  • Gemini platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini platform
  • IONOS Cloud GPU Servers
    4.6 out of 5 stars 45,816 Ratings
    Visit Website for IONOS Cloud GPU Servers
  • RaimaDB
    4.8 out of 5 stars 12 Ratings
    Visit Website for RaimaDB
  • Nexo
    4.4 out of 5 stars 18,841 Ratings
    Visit Website for Nexo
  • 10Duke
    4.8 out of 5 stars 8 Ratings
    Visit Website for 10Duke
  • Google Cloud Speech-to-Text
    4.5 out of 5 stars 446 Ratings
    Visit Website for Google Cloud Speech-to-Text
  • RetailEdge
    4.8 out of 5 stars 201 Ratings
    Visit Website for RetailEdge
  • Compute with Hivenet
    5.0 out of 5 stars 4 Ratings
    Visit Website for Compute with Hivenet
  • Careerminds
    4.9 out of 5 stars 46 Ratings
    Visit Website for Careerminds
Inkling 2 Mini:

About

Inkling 2 Mini is an open-weight artificial intelligence model developed by Thinking Machines Lab for advanced reasoning, autonomous coding, tool use, and efficient local inference. The model uses a looped Mixture-of-Experts transformer architecture with 26.4 billion total parameters and 3.4 billion active parameters, repeatedly processing information through its middle layers to improve reasoning performance. Its optimized architecture enables the model to complete complex tasks using fewer reasoning tokens while maintaining computational efficiency. Inkling 2 Mini supports agentic software development, web research, visual understanding, document analysis, and multistep problem-solving workflows. With a memory footprint of approximately 20GB, the model can operate locally on compatible laptops and desktop computers, including Macs with at least 32GB of RAM.
Nemotron 3 Ultra:

About

Nemotron 3 Nano is a compact, open large language model in NVIDIA’s Nemotron 3 family, designed for efficient agentic reasoning, conversational AI, and coding tasks. It uses a hybrid Mixture-of-Experts Mamba-Transformer architecture that activates only a small subset of parameters per token, enabling low-latency inference while maintaining strong accuracy and reasoning performance. It has approximately 31.6 billion total parameters with around 3.2 billion active (3.6 billion including embeddings), allowing it to achieve higher accuracy than previous Nemotron 2 Nano while using less computation per forward pass. Nemotron 3 Nano supports long-context processing of up to one million tokens, enabling it to handle large documents, multi-step workflows, and extended reasoning chains in a single pass. It is designed for high-throughput, real-time execution, excelling in multi-turn conversations, tool calling, and agent-based workflows where tasks require planning, reasoning, and more.
Inkling 2 Mini:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
Nemotron 3 Ultra:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
Inkling 2 Mini:

Audience

AI developers, machine learning engineers, software engineers, AI researchers, autonomous agent developers, and organizations seeking open-weight reasoning models for local inference, agentic coding, tool integration, and customizable AI applications
Nemotron 3 Ultra:

Audience

AI developers and engineers requiring a tool to build agentic systems capable of long-context reasoning, coding, and real-time multi-step workflows
Inkling 2 Mini:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Nemotron 3 Ultra:

Support

Phone Support Supported
24/7 Live Support Not Supported
Online Supported
Inkling 2 Mini:

API

Offers API Supported
Nemotron 3 Ultra:

API

Offers API Not Supported
Inkling 2 Mini:

Screenshots and Videos

Nemotron 3 Ultra:

Screenshots and Videos

Inkling 2 Mini:

Pricing

$0.15 per 1M input tokens
$0.15 per 1M input tokens, $0.50 per 1M output tokens, and $0.015 per 1M cache hit tokens
Free Version Not Supported
Free Trial Not Supported
Nemotron 3 Ultra:

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported
Inkling 2 Mini:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
Nemotron 3 Ultra:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
Inkling 2 Mini:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
Nemotron 3 Ultra:

Training

Documentation Supported
Webinars Supported
Live Online Supported
In Person Not Supported
Inkling 2 Mini:

Company Information

Thinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/
Nemotron 3 Ultra:

Company Information

NVIDIA
Founded: 1993
United States
research.nvidia.com/labs/nemotron/Nemotron-3/
Inkling 2 Mini:

Alternatives

GPT-6 Luna

GPT-6 Luna

OpenAI
5.0 out of 5 stars
Nemotron 3 Ultra:

Alternatives

Claude Opus 5.5

Claude Opus 5.5

Anthropic
5.0 out of 5 stars
Inkling 2 Mini:
Nemotron 3 Ultra:
Claude Sonnet 5.5

Claude Sonnet 5.5

Anthropic
5.0 out of 5 stars
Inkling 2 Mini:
Kimi K3.1 Pro

Kimi K3.1 Pro

Moonshot AI
5.0 out of 5 stars
Nemotron 3 Ultra:
Claude Fable 5.1

Claude Fable 5.1

Anthropic
5.0 out of 5 stars
Inkling 2 Mini:
Inkling 2 Small

Inkling 2 Small

Thinking Machines Lab
Nemotron 3 Ultra:
Inkling 2 Mini:
Inkling-Small

Inkling-Small

Thinking Machines Lab
5.0 out of 5 stars
Nemotron 3 Ultra:
Inkling 2 Mini:

Categories

Nemotron 3 Ultra:

Categories

Inkling 2 Mini:

Integrations

Model Context Protocol (MCP) Supported
Nemotron 3 Not Supported
OpenTag Not Supported
Tinker Supported
Nemotron 3 Ultra:

Integrations

Model Context Protocol (MCP) Not Supported
Nemotron 3 Supported
OpenTag Supported
Tinker Not Supported
Inkling 2 Mini:
Claim Inkling 2 Mini and update features and information
Claim Inkling 2 Mini and update features and information
Nemotron 3 Ultra:
Claim Nemotron 3 Ultra and update features and information
Claim Nemotron 3 Ultra and update features and information