inkling

TokenSpeed is a speed-of-light LLM inference engine.

CPU-first, eager-execution tensor/autograd runtime and LLM inference engine written in pure Zig

Run Thinking Machines Lab's Inkling (975B-A41B MoE, multimodal) on Apple Silicon with MLX — 4/6/8-bit.

Faster attention kernels for serving TML's Inkling model on vLLM. 2.7x over the shipping path on H100, and the only implementation that runs on A100.

Samples and documentation for using VP Link with Microsoft Bonsai

Tools for converting vector graphics from the Wacom Inkling device

Is Inkling AI the Ultimate Open Source Model? Full Test - A 975B Mixture-of-Experts (MoE) multimodal foundation model by Thinking Machines, with local setups for vLLM, SGLang, Hugging Face, TokenSpeed, and Unsloth, plus three advanced agentic/epistemic benchmarks.

A set of documents, fonts, and other utilities to aid in support of the Inkling fan-language.

Temporary Inkling Small compatibility patch for oMLX on Apple Silicon

Evaluating if Inkling (MoE model by Thinking Machines) can perform well in the context of high-level self-driving reasoning.

Self-hosted AI résumé screening with a built-in bias audit. Fine-tuned Inkling model, calibrated scores, blind review, human-in-the-loop. Your data never leaves.

Agentic terminal chatbot for thinkingmachines/Inkling — tool use, permission policy engine, and a glass TUI

the image files for the boo-yah doc