New Model: Inkling by Thinking Machine on Hugging Face
Inkling by Thinking Machines is here, a 1 TRILLION parameter open model that natively understands images, text, AND audio, with a 1M token context window. In this video, we break down the architecture, show you how to run it, and share our vibe-eval results. Now on Hugging Face 🤗 https://huggingface.co/thinkingmachin... ⚡ TL;DR • 975B total / 41B active params (MoE, 256 experts) • Native image, text & audio input — one model, no separate encoders • 1M context window, trained on 45T tokens • BF16 + calibrated NVFP4 checkpoints, MTP layers for speculative decoding • Day-0 support: transformers, SGLang, vLLM, llama.cpp ⏱️ CHAPTERS 00:00 Intro — what is Inkling? 00:00 Architecture deep dive (relative attention, hybrid attention, SConv) 00:00 MoE with shared expert sinks 00:00 Vision & audio towers explained 00:00 Running it: transformers pipeline 00:00 Serving with SGLang & vLLM 00:00 Free inference via Inference Providers 00:00 1-bit GGUFs with llama.cpp & Unsloth 00:00 Agentic coding demo with Pi 00:00 MTP speculative decoding 00:00 Vision & audio vibe evals 00:00 Post-training with tinker + OpenEnv 00:00 Benchmarks & final thoughts 🔧 TRY IT • Model (BF16): https://huggingface.co/thinkingmachin... • Model (NVFP4): https://huggingface.co/thinkingmachin... • GGUF quants: https://huggingface.co/unsloth/inklin... • Inference Providers (free for 2h at launch): https://huggingface.co/thinkingmachin... • Quick start: pip install -U transformers, then pipeline("any-to-any", model="thinkingmachines/Inkling") 📚 RESOURCES • Full blog post: https://huggingface.co/blog/thinkingm... • Vibe eval images & results: https://huggingface.co/buckets/merve/... • RL example (tinker + OpenEnv): https://github.com/huggingface/OpenEnv • Distillation with TRL (GOLD): https://github.com/huggingface/trl 💡 KEY TAKEAWAYS • Needs ~2TB VRAM in BF16 (600GB in NVFP4) — but 1-bit GGUFs retain ~74% top-1 accuracy at 86% smaller • Reasoning effort is tunable from "none" to "max"; medium (0.7) is the sweet spot • The model transcribes/OCRs inputs first, then reasons — prompt accordingly • Great for multimodal reasoning apps, document processing, and fine-tuning 👥 By burtenshaw, merve, pcuenq & ariG23498 from Hugging Face #Inkling #ThinkingMachines #HuggingFace #OpenSource #LLM #Multimodal #AI #MachineLearning

Things To Notice On Your Next Flight

Inkling First Look & Test – Thinking Machines 1T Parameter Open Model!

The World's Best Stock Market Is Also Crashing!

Candidate Selection - The Selection Problem (Agentic Pipeline #29)

Inkling: Why Thinky's Open Model May Change "Everything"

New #1 open source AI model is here! FABLE LEVEL
![[Emergency Episode] Moonshot’s Kimi K3 has Arrived! China has a Frontier Model](https://i.ytimg.com/vi/hPb3SESIjdU/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCDXmfByv2-YChIq9cfr9td5PUmfA)
[Emergency Episode] Moonshot’s Kimi K3 has Arrived! China has a Frontier Model

MCP vs API: Why traditional APIs are failing AI agents

MiniCPM5 - Just How Good Can a 1B Model Be?

The Great Bun Rewrite

Haskell is DONE

Is This the Biggest AI Release of 2026? (China’s New DeepSeek Moment)

Kimi K3 CRUSHED Fable

THIS is AMD's New 144GB HBM3E PCIe GPU AMD Instinct MI350P

Training Agents: Live tutorial on how to fine-tune a coding agent for continual learning

Welcome to Open Source AI: Run Your Own Models Locally

We got addicted to an AI model we can't talk about

Can AI Come Up With Original Ideas?

Hermes Architecture EXPLAINED: Memory, Context & Gateways

