Inkling-Small

Inkling-Small

Thinking Machines Lab
5.0 out of 5 stars
Inkling-Small Step 3.5 Flash

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
  • Buildium
    4.5 out of 5 stars 2,563 Ratings
    Visit Website for Buildium
  • RetailEdge
    4.8 out of 5 stars 201 Ratings
    Visit Website for RetailEdge
  • TIMi
    4.9 out of 5 stars 68 Ratings
    Visit Website for TIMi
  • Acadia
    5.0 out of 5 stars 3 Ratings
    Visit Website for Acadia
  • Fraud.net
    4.7 out of 5 stars 57 Ratings
    Visit Website for Fraud.net
  • rezStream Cloud PMS
    4.7 out of 5 stars 126 Ratings
    Visit Website for rezStream Cloud PMS
  • Arlo Training Management Software
    4.6 out of 5 stars 243 Ratings
    Visit Website for Arlo Training Management Software
  • isoTracker Quality Management
    4.6 out of 5 stars 19 Ratings
    Visit Website for isoTracker Quality Management
Inkling-Small:

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.
Step 3.5 Flash:

About

Step 3.5 Flash is an advanced open source foundation language model engineered for frontier reasoning and agentic capabilities with exceptional efficiency, built on a sparse Mixture of Experts (MoE) architecture that selectively activates only about 11 billion of its ~196 billion parameters per token to deliver high-density intelligence and real-time responsiveness. Its 3-way Multi-Token Prediction (MTP-3) enables generation throughput in the hundreds of tokens per second for complex multi-step reasoning chains and task execution, and it supports efficient long contexts with a hybrid sliding window attention approach that reduces computational overhead across large datasets or codebases. It demonstrates robust performance on benchmarks for reasoning, coding, and agentic tasks, rivaling or exceeding many larger proprietary models, and includes a scalable reinforcement learning framework for consistent self-improvement.
Inkling-Small:

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
Step 3.5 Flash:

Platforms Supported

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

Audience

AI researchers and developers seeking an efficient open-weight multimodal model for reasoning, agentic tasks, and lower-cost deployment
Step 3.5 Flash:

Audience

Developers, researchers, and AI engineers who want a powerful open source foundational AI model capable of fast, deep reasoning, coding assistance, and agentic task execution
Inkling-Small:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Step 3.5 Flash:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Inkling-Small:

API

Offers API Supported
Step 3.5 Flash:

API

Offers API Supported
Inkling-Small:

Screenshots and Videos

Step 3.5 Flash:

Screenshots and Videos

Inkling-Small:

Pricing

$0.30 per million input tokens
$0.30 per million input tokens and $1.20 per million output tokens
Free Version Not Supported
Free Trial Not Supported
Step 3.5 Flash:

Pricing

Free
Free Version Supported
Free Trial Not Supported
Inkling-Small:

Reviews/Ratings

Overall 5.0 / 5
features 4.0 / 5
Step 3.5 Flash:

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-Small:

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.
Inkling-Small:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
Step 3.5 Flash:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
Inkling-Small:

Company Information

Thinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/news/inkling-small/
Step 3.5 Flash:

Company Information

StepFun
Founded: 2023
China
static.stepfun.com/blog/step-3.5-flash/
Inkling-Small:

Alternatives

Muse Spark Open

Muse Spark Open

Meta
5.0 out of 5 stars
Step 3.5 Flash:

Alternatives

Inkling-Small:
GPT-5.6 Luna

GPT-5.6 Luna

OpenAI
5.0 out of 5 stars
Step 3.5 Flash:
Inkling-Small:
Inkling

Inkling

Thinking Machines Lab
Step 3.5 Flash:
MiMo-V2-Flash

MiMo-V2-Flash

Xiaomi Technology
Inkling-Small:
Inkling 2 Small

Inkling 2 Small

Thinking Machines Lab
Step 3.5 Flash:
Beam

Beam

Reflection
Inkling-Small:
SWE-2 Flash

SWE-2 Flash

Cognition
5.0 out of 5 stars
Step 3.5 Flash:
Qwen3.5

Qwen3.5

Alibaba
Inkling-Small:

Categories

Step 3.5 Flash:

Categories

AI Models Supported
Foundation Models Supported
Inkling-Small:

Integrations

GitHub Not Supported
Hugging Face Not Supported
Model Context Protocol (MCP) Supported
ModelScope Not Supported
Tinker Supported
arXiv Not Supported
Step 3.5 Flash:

Integrations

GitHub Supported
Hugging Face Supported
Model Context Protocol (MCP) Not Supported
ModelScope Supported
Tinker Not Supported
arXiv Supported
Inkling-Small:
Claim Inkling-Small and update features and information
Claim Inkling-Small and update features and information
Step 3.5 Flash:
Claim Step 3.5 Flash and update features and information
Claim Step 3.5 Flash and update features and information