Inkling-Small

Inkling-Small

Thinking Machines Lab
Pokee-Isaac

Pokee-Isaac

Pokee AI
+
+

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
  • NeuBird
    2 Ratings
    Visit Website
  • Buildium
    2,545 Ratings
    Visit Website
  • RetailEdge
    201 Ratings
    Visit Website
  • TIMi
    68 Ratings
    Visit Website
  • UENI
    9,369 Ratings
    Visit Website
  • Fraud.net
    56 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

Pokee-Isaac text-only agentic model with a usable context window of up to 10 million tokens. It is designed to reason, plan, call tools, and execute long-horizon tasks while remaining small enough to deploy inside a VPC, on customer premises, on a workstation, or on-device. Pokee reports that Isaac maintains strong long-context performance across RULER from 256K through 10M tokens and leads the evaluated panel on multi-needle retrieval at 256K, 512K, and 1M. Its agentic architecture is built for deterministic function calling, sustained multi-turn coherence, real-shell execution, and discovering and composing tools across live MCP servers. In Pokee’s controlled benchmarks, Isaac ranked first on BFCL v4 and τ³-bench, second on the Terminal-Bench 2.1 text-only subset, and third on MCP-Atlas. Security testing with DTAP also showed the lowest combined attack success rate in the comparison panel while retaining strong benign-task performance.

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

Developers, AI agent builders, software engineering teams, research teams, enterprise AI teams, multimodal application developers, coding assistant builders, tool-use workflow teams, and organizations that need efficient reasoning, long-context processing, text-image-audio understanding, adjustable thinking effort, coding performance, and scalable Mixture-of-Experts inference

Audience

AI infrastructure teams that need long-context, tool-using models they can deploy privately across cloud, on-premises, workstation, or edge hardware

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

$0.15 per 1M tokens
Free Version
Free Trial

Reviews/Ratings

Overall 5.0 / 5
features 4.0 / 5

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

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

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

Company Information

Pokee AI
Founded: 2024
United States
console.pokee.ai/model

Alternatives

Alternatives

Poke

Poke

The Interaction Company
Inkling

Inkling

Thinking Machines Lab
ISAAC

ISAAC

ISAAC Instruments
GLM-5

GLM-5

Zhipu AI

Categories

Categories

Integrations

Model Context Protocol (MCP)
Pokee AI
Tinker

Integrations

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