TextImage + text

Inkling

Flagship open models from Mira Murati's lab: they take text, images and audio. Large MoE models that need several GPUs.

Developer
Thinking Machines Lab, USA
First release
Jul 2026
Latest release
Jul 2026
Sizes
276B-A12B, 975B-A41B
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Software development, Finance, Documents and accounting
Deploy on your server Hugging Face

What it does

  • Flagship-level corporate assistant
  • Analysis of documents, images and audio
  • Programming help
  • Agents for complex multi-step tasks

Where it is used

Large companiesIT and developmentAnalytics

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Inkling-Small
  2. Inkling

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Inkling be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Inkling need?

At minimum: Server with several GPUs — flagship versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Inkling support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Inkling and what does it cost?

The Inkling weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextCohere CommandCohere · CanadaCommercial use with conditions

Business models: document search with source citations, tool calling, many languages. Command A+ (2026) was the first under Apache 2.0, followed by the North line: code, translation and compact vision.

DetailsTextNVIDIA NemotronNVIDIA · USACommercial use with conditions

NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only). The new Nemotron 3.5 Super VL (120B, 12B active, up to 1M-token context) reads text, images and video up to two minutes, with a focus on documents and agents; the compressed Bolt (74B, 9B active) fits into 24 GB of video memory. Super VL languages: English, Spanish, French, German, Italian, Japanese. Dory 1.0 (4B, up to 256K-token context, English) runs the same block of layers several times, and the number of passes can be changed per task: more passes give more accuracy without a new model and without long reasoning in the text.

DetailsTextDeepSeekDeepSeek · ChinaCommercial use allowed

DeepSeek's flagship line: from the first 7B/67B to V4-Pro with 1.6 trillion parameters. Closed-model quality under an open MIT license; V4-Flash-Vision-Exp and V4.1-Flash understand images, context up to 1M tokens. The fresh V4.1-Flash-1017 answers shorter and faster than the previous Flash: by the measurements of DeepSeek itself, 77.0 vs 74.2 on DeepSWE v1.1 and 42.3 vs 31.2 on Terminal-Bench 4.0.

Details

Source: huggingface.co/thinkingmachines/Inkling-Small. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.