Pyyan / Compare / Inkling 2 Small vs MiMo-V2.6-Pro

Inkling 2 Small vs MiMo-V2.6-Pro

2 of 5

Open-Weight Models · verified 14 Nov 2026

TInkling 2 SmallThinking Machines Labcurrent
XMiMo-V2.6-ProXiaomicurrent
3 slots left
SpecificationInkling 2 SmallMiMo-V2.6-Pro
SummaryA 594B multimodal model with 17B active, trained natively in 4-bit NVFP4, under Apache 2.0.A trillion parameters under the MIT licence.
Context1M1M
Input ($/Mtok)Weights onlyWeights only
Output ($/Mtok)Weights onlyWeights only
LicenceApache 2.0MIT
Max outputNot publishedNot published
Parameters594B total, 17B active1.02T total, 42B active
Released5 Nov 2026, weights 12 Nov21 Sep 2026
Model IDthinkingmachines/Inkling-2-SmallXiaomiMiMo/MiMo-V2.6-Pro
CategoryOpen-Weight ModelsOpen-Weight Models
OfficialThinking Machines Lab ↗Xiaomi ↗

Highlighted rows are where these differ.

Inkling 2 Small

  • Weights published on Hugging Face on 12 November 2026, a week after a hosted-only launch on Tinker on 5 November
  • Takes text and images, writes text, with a context window of up to 1M tokens
  • Pretrained, midtrained and post-trained in NVFP4. The main checkpoint needs at least 500GB of GPU memory, such as 2 B300s or 4 H200s
  • An MXFP8 checkpoint is also published and needs at least 800GB. The lab says it scores only 1 to 2 points higher
  • Local serving recipes for SGLang, vLLM, TokenSpeed and Unsloth. The benchmark scores on the card are the lab's own

Best for self-hosting a large text and image model on a multi-GPU node, or fine-tuning it on Tinker.

Full spec sheet →

MiMo-V2.6-Pro

  • 1.02T total parameters, 42B active per token, a 4.1% activation ratio
  • Text, image, video and audio in, with a 1M token context
  • Shipped with 7,000+ reinforcement learning environments and the framework that trained it

Best for multimodal work on your own cluster.

Full spec sheet →