DeepSWE

DeepSWE

Agentica Project
Inkling-Small

Inkling-Small

Thinking Machines Lab
+
+

Related Products

  • Gemini Enterprise Agent Platform
    999 Ratings
    Visit Website
  • Checksum.ai
    1 Rating
    Visit Website
  • JetBrains Junie
    12 Ratings
    Visit Website
  • Aikido Security
    239 Ratings
    Visit Website
  • Google AI Studio
    30 Ratings
    Visit Website
  • SuperOps
    223 Ratings
    Visit Website
  • QA Wolf
    269 Ratings
    Visit Website
  • Creatio
    586 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Parasoft
    148 Ratings
    Visit Website

About

DeepSWE is a fully open source, state-of-the-art coding agent built on top of the Qwen3-32B foundation model and trained exclusively via reinforcement learning (RL), without supervised finetuning or distillation from proprietary models. It is developed using rLLM, Agentica’s open source RL framework for language agents. DeepSWE operates as an agent; it interacts with a simulated development environment (via the R2E-Gym environment) using a suite of tools (file editor, search, shell-execution, submit/finish), enabling it to navigate codebases, edit multiple files, compile/run tests, and iteratively produce patches or complete engineering tasks. DeepSWE exhibits emergent behaviors beyond simple code generation; when presented with bugs or feature requests, the agent reasons about edge cases, seeks existing tests in the repository, proposes patches, writes extra tests for regressions, and dynamically adjusts its “thinking” effort.

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.

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

Software engineers, researchers, and developers seeking a solution to assist with real-world coding tasks such as bug-fixing, pull-request automation, and multi-file code edits

Audience

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

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

Free
Free Version
Free Trial

Pricing

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

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
features 4.0 / 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.

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Agentica Project
Founded: 2025
United States
agentica-project.com

Company Information

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

Alternatives

Devstral 2

Devstral 2

Mistral AI

Alternatives

Devstral Small 2

Devstral Small 2

Mistral AI
DeepCoder

DeepCoder

Agentica Project
Qwen2.5-Max

Qwen2.5-Max

Alibaba
Inkling

Inkling

Thinking Machines Lab
KAT-Coder-Pro V2

KAT-Coder-Pro V2

StreamLake

Categories

Categories

Integrations

Model Context Protocol (MCP)
Tinker
Together AI

Integrations

Model Context Protocol (MCP)
Tinker
Together AI
Claim DeepSWE and update features and information
Claim DeepSWE and update features and information
Claim Inkling-Small and update features and information
Claim Inkling-Small and update features and information