Inkling 2 Small

Inkling 2 Small

Thinking Machines Lab
Muse Spark Open

Muse Spark Open

Meta
5.0 out of 5 stars
+
+

Related Products

  • Gemini Enterprise Agent Platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini Enterprise Agent Platform
  • LTX
    4.4 out of 5 stars 182 Ratings
    Visit Website for LTX
  • Nexo
    4.4 out of 5 stars 18,841 Ratings
    Visit Website for Nexo
  • Josys
    4.4 out of 5 stars 263 Ratings
    Visit Website for Josys
  • Checksum.ai
    5.0 out of 5 stars 2 Ratings
    Visit Website for Checksum.ai
  • Dialpad Support
    4.4 out of 5 stars 1,629 Ratings
    Visit Website for Dialpad Support
  • Creatio
    4.6 out of 5 stars 589 Ratings
    Visit Website for Creatio
  • SearchUnify
    4.5 out of 5 stars 150 Ratings
    Visit Website for SearchUnify
  • Cloverleaf
    4.8 out of 5 stars 189 Ratings
    Visit Website for Cloverleaf
  • GWI
    4.4 out of 5 stars 201 Ratings
    Visit Website for GWI

About

Inkling 2 Small is a multimodal AI model developed by Thinking Machines Lab for advanced reasoning, autonomous software engineering, visual understanding, and AI agent development. The model uses a mixture-of-experts architecture with 594 billion total parameters and 17 billion active parameters to balance intelligence and computational efficiency. It supports text and image inputs, a context window of up to one million tokens, and configurable reasoning effort for tasks requiring different levels of analysis. Its agentic capabilities enable autonomous code generation, debugging, website development, scientific research, and complex multistep workflows involving external tools. Inkling 2 Small also supports fine-tuning and reinforcement learning through Thinking Machines Lab's Tinker platform, allowing developers to customize the model for specialized applications.

About

Muse Spark Open is an open-weight, natively multimodal language model for developers and organizations building AI applications, coding systems, and agentic workflows. The released model has 816 billion total parameters, 42 billion active parameters, and a 1-million-token context window. Teams can download the model weights, run inference through supported engines such as vLLM, SGLang, TensorRT-LLM, Hugging Face Transformers, Apple MLX, llama.cpp, or Unsloth, and customize the model using PyTorch. It supports long-context reasoning, software engineering, coding, tool use, and multimodal inputs. Deployment options include cloud inference through listed API providers or self-hosting on compatible GPU systems; Meta documents a desktop setup using two Apple M5 Ultra Mac Studio computers. The model is released under the Muse Model License with limited commercial terms.

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

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Supported
On-Premises Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

AI developers, machine learning engineers, software developers, autonomous agent researchers, data scientists, AI research laboratories, DevOps professionals, computational scientists, enterprise AI teams, and organizations seeking multimodal language models, long-context reasoning, AI coding agents, reinforcement learning, model fine-tuning, visual understanding, and autonomous research capabilities

Audience

AI developers, machine learning engineers, software engineers, AI researchers, enterprise development teams, and organizations seeking customizable open-weight multimodal models for local inference, autonomous agents, complex coding, and long-context AI applications

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Not Supported

API

Offers API Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

$0.30 per million input tokens
$0.30 per million input tokens, $0.03 per million cached input tokens, and $1.00 per million output tokens
Free Version Not Supported
Free Trial Not Supported

Pricing

$0
Model weights are available at no charge under the Muse Model License, which has limited commercial-use terms. Hosted inference providers set their own usage prices.
Free Version Supported
Free Trial Not Supported

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

Reviews/Ratings

Overall 5.0 / 5
ease 5.0 / 5

Pros & Cons from Real Users

Pros

  • Meta finally opened up a genuinely frontier-level Muse model. The 1M-token context window and 42B active parameters make it strong enough for large repos, long agent sessions, multimodal work, and complex coding without feeling like a stripped-down open model. The local deployment story is also a huge deal. Being able to run something this capable on two M5 Ultra Mac Studios is impressive, especially for teams that want more control over data, infrastructure, and customization. I also like how much of the stack is open around it. Muse Spark Open works with MLX, vLLM, SGLang, TensorRT-LLM, Transformers, llama.cpp, and Unsloth, and Meta is making the weights available through Hugging Face, SageMaker, Google Cloud Model Garden, and Microsoft Foundry.

Cons

  • Even though it is technically desktop-capable, needing two M5 Ultra Mac Studios for the full local experience is still a serious setup, so most developers will probably use hosted inference instead.

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

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

Company Information

Meta
Founded: 2004
United States
research.meta.ai/blog/muse-spark-open

Alternatives

GPT-6 Luna

GPT-6 Luna

OpenAI
5.0 out of 5 stars

Alternatives

Claude Fable 5.2

Claude Fable 5.2

Anthropic
5.0 out of 5 stars
Kimi K3.1 Pro

Kimi K3.1 Pro

Moonshot AI
5.0 out of 5 stars
GPT-6.1 Terra

GPT-6.1 Terra

OpenAI
5.0 out of 5 stars
Inkling-Small

Inkling-Small

Thinking Machines Lab
5.0 out of 5 stars
Recursive Flint

Recursive Flint

Recursive
Inkling

Inkling

Thinking Machines Lab
Muse Glimmer

Muse Glimmer

Meta
5.0 out of 5 stars

Categories

Categories

Integrations

Baseten Not Supported
Fireworks AI Not Supported
Groq Not Supported
Hugging Face Not Supported
Modal Not Supported
Model Context Protocol (MCP) Supported
Nebius Not Supported
OpenRouter Not Supported
Tinker Supported
Together AI Not Supported
vLLM Not Supported

Integrations

Baseten Supported
Fireworks AI Supported
Groq Supported
Hugging Face Supported
Modal Supported
Model Context Protocol (MCP) Not Supported
Nebius Supported
OpenRouter Supported
Tinker Not Supported
Together AI Supported
vLLM Supported
Claim Inkling 2 Small and update features and information
Claim Inkling 2 Small and update features and information
Claim Muse Spark Open and update features and information
Claim Muse Spark Open and update features and information