Inkling-Small

Inkling-Small

Thinking Machines Lab
+
+

Related Products

  • Gemini Enterprise Agent Platform
    999 Ratings
    Visit Website
  • TrustInSoft Analyzer
    6 Ratings
    Visit Website
  • LTX
    182 Ratings
    Visit Website
  • Checksum.ai
    1 Rating
    Visit Website
  • Buildium
    2,545 Ratings
    Visit Website
  • RetailEdge
    201 Ratings
    Visit Website
  • TIMi
    68 Ratings
    Visit Website
  • Fraud.net
    56 Ratings
    Visit Website
  • PackageX OCR Scanning
    48 Ratings
    Visit Website
  • rezStream Cloud PMS
    126 Ratings
    Visit Website

About

Inkling-Small is an efficient model that offers performance comparable to Inkling at a quarter of its size. It is a Mixture-of-Experts transformer with 276 billion total parameters and 12 billion active parameters, trained on NVIDIA GB300 NVL72 systems. It supports native reasoning across text, images, and audio, variable thinking effort, and context windows of up to one million tokens. Users adjust reasoning effort from minimal to extra high to balance performance and compute. Improved pre-training data, post-training with on-policy distillation from Inkling, and extended agentic coding reinforcement learning helped Inkling-Small surpass its larger counterpart on reasoning and coding benchmarks. It performs well in coding and tool-use harnesses, exceeds 80% on SWE-bench Verified, and combines strong reasoning with efficient output. Its encoder-free multimodal architecture processes audio as dMel spectrograms and images as 40-by-40-pixel patches alongside text tokens.

About

Muse Spark 1.2 is Meta’s coding-focused model update designed to power Muse Code and improve software engineering workflows. The model is built for code generation, complex debugging, codebase understanding, long-horizon development tasks, and end-to-end developer workflows. Muse Spark 1.2 was co-trained with Muse Code to improve performance inside the terminal coding agent environment. It supports planning, goal conditioning, context compaction, subagent coordination, and iterative coding workflows across large repositories. The model was trained with expanded coding compute, diverse development environments, self-improvement loops, and long-running engineering tasks. Built for AI developers and software teams, Muse Spark 1.2 helps agents plan, write, validate, debug, and optimize code with greater autonomy.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

AI researchers and developers seeking an efficient open-weight multimodal model for reasoning, agentic tasks, and lower-cost deployment

Audience

AI developers, software engineers, coding agent builders, research teams, platform teams, DevOps teams, ML engineers, enterprise development teams, and organizations that need code generation, debugging, codebase understanding, long-horizon coding, terminal agents, subagent coordination, repository automation, kernel optimization, and end-to-end developer workflow support

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

$0.30 per million input tokens
$0.30 per million input tokens and $1.20 per million output tokens
Free Version
Free Trial

Pricing

$1.25 per 1M tokens (input)
$1.25 per million tokens in input, and $4.25 per million tokens of output
Free Version
Free Trial

Reviews/Ratings

Overall 5.0 / 5
features 4.0 / 5

Reviews/Ratings

Overall 5.0 / 5
ease 5.0 / 5
features 5.0 / 5
design 5.0 / 5

Pros & Cons from Real Users

Pros

  • Inkling-Small is really interesting from a developer’s point of view because it hits a sweet spot between serious model capability and practical deployability. A 276B-parameter model with only 12B active parameters per token is exactly the kind of architecture that makes sense if you care about cost, speed, and scaling real AI workflows. I also like that it is open weights under Apache 2.0. That makes it way more appealing for developers who want to fine-tune, inspect, customize, or build on top of the model without being completely locked into a closed API. The multimodal support is a big plus too. Being able to work with text, images, and audio inputs gives Inkling-Small a lot of room for developer tools, coding agents, support bots, document workflows, and internal automation.

Cons

  • The main downside is that “small” here is still not tiny. Even with only 12B active parameters, this is still a large open model that will require real infrastructure if you want to host it yourself. I would also want to test it deeply before making it the backbone of a production coding agent. The model card and early coverage look promising, but real developer workflows expose problems that benchmarks do not always catch: messy repos, flaky tests, weird dependencies, tool failures, and long multi-step tasks.

Pros & Cons from Real Users

Pros

  • Muse Spark 1.2 looks like a big step up for developers because it is clearly aimed at real software engineering work, not just casual code suggestions. The fact that it powers Muse Code makes it feel more practical right away, especially for terminal-based workflows where the model can help write code, validate changes, and work through bigger tasks. I like that Meta seems to be pushing hard into agentic coding. Earlier Muse Spark versions were already positioned around multimodal reasoning, tool use, and visual coding, and 1.2 feels like the more developer-focused evolution of that direction. The cost angle is interesting too. Reports mention Muse Code having multiple pricing tiers, including a cheaper option, which could matter a lot for developers running coding agents frequently instead of only using AI once in a while.

Cons

  • It is still new and tied to a beta coding agent, so I would not trust it blindly yet. I would want to test it on real repos, messy bugs, failing tests, multi-file edits, and longer agent runs before making it part of my daily stack. Meta also still has to prove the developer experience. A strong model is one thing, but coding agents live or die on tooling, speed, reliability, permissions, logs, diffs, and how well they recover when something breaks.

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Thinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/news/inkling-small/

Company Information

Meta
Founded: 2004
United States
meta.ai

Alternatives

Alternatives

GPT-5.6 Sol

GPT-5.6 Sol

OpenAI
Inkling

Inkling

Thinking Machines Lab

Categories

Categories

Integrations

Model Context Protocol (MCP)
.NET
C#
CSS
Codex CLI
Continue
Dart
Hermes Agent
Instagram
Kotlin
Meta Model API
Odysseus
OpenAI Codex
OpenClaw
OpenCode
Python
R
Solidity
Vercel AI SDK
WhatsApp

Integrations

Model Context Protocol (MCP)
.NET
C#
CSS
Codex CLI
Continue
Dart
Hermes Agent
Instagram
Kotlin
Meta Model API
Odysseus
OpenAI Codex
OpenClaw
OpenCode
Python
R
Solidity
Vercel AI SDK
WhatsApp
Claim Inkling-Small and update features and information
Claim Inkling-Small and update features and information
Claim Muse Spark 1.2 and update features and information
Claim Muse Spark 1.2 and update features and information