Pyyan / Compare / Inkling 2 Small vs DeepSeek V4-Pro

Inkling 2 Small vs DeepSeek V4-Pro

2 of 5

Open-Weight Models · verified 14 Nov 2026

TInkling 2 SmallThinking Machines Labcurrent
DeepSeek V4-ProDeepSeekcurrent
3 slots left
SpecificationInkling 2 SmallDeepSeek V4-Pro
SummaryA 594B multimodal model with 17B active, trained natively in 4-bit NVFP4, under Apache 2.0.Best all-round open model of 2026.
Context1M—
Input ($/Mtok)Weights only—
Output ($/Mtok)Weights only—
LicenceApache 2.0MIT
Max outputNot published—
Parameters594B total, 17B active—
Released5 Nov 2026, weights 12 Nov—
Model IDthinkingmachines/Inkling-2-Small—
CategoryOpen-Weight ModelsOpen-Weight Models
OfficialThinking Machines Lab ↗DeepSeek ↗

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 →

DeepSeek V4-Pro

  • Tops open leaderboards on agentic coding and reasoning
  • MIT licence — no conditions
  • Pioneered aggressive cache-hit pricing at ~$0.07/M
  • DeepSeek routes all V4-Pro requests to V4.1 Flash from 14 September 2026

Best for everything open.

Full spec sheet →