All models

Inkling

bythinkingmachinesthinkingmachines· 15 Jul 2026
General purposeMultimodal

The first model from Thinking Machines is a 975B-A41B multimodal MoE that supports text, images, and audio as inputs and produces text as output. While it is not the strongest model among peers (in China) in its size class, it is positioned to be a great base for fine-tuning, e.g., through their commercial offering, Tinker. They also release a smaller version (276B-A12B), which is really competitive for its size.

Specs
Params975B (41B active)
LicenseApache-2.0
Capability · Artificial Analysis
AA Index
25.5
Months Behind Frontier
7.9 mo
gemini-3-pro
18 Nov 2025
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.19×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
329.7K
last 30d
461.3K
all time
HF Likes
1.8K

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Inference · OpenRouter
Tokens/Day
52.5B
7d avg · listed 6/7
Peak Tokens/Day
67.7B
08 Sep 2026
Peak Rank
#37
06 Sep 2026

OpenRouter publishes daily token totals for its ~50 most-served models. Days missing from the chart mean Inkling fell below that cutoff — not zero usage. OpenRouter logs usage separately per dated model version and per variant (like ":free"); the hub combines provider variants while keeping separately cataloged releases distinct.

Related Models