Thinking Machines Launches Inkling-Small: 12B Active Params Beats Larger Model
mervenoyann · x · 2026-07-31
Thinking Machines Lab has released Inkling-Small. The model has 276B total parameters but only 12B active parameters (MoE architecture), and it outperforms the larger Inkling model on coding tasks.
Key Features:
- Native Multimodal: Natively accepts and processes image, text, and audio inputs.
- Massive Context: Supports a vast 1M context window.
- Efficient Deployment: Available in BF16, NVFP4, and MXFP8 weight variants, featuring speculative MTP layers for faster inference.
Ecosystem: Offers one-click deployment on Hugging Face Inference Endpoints (up to 160 TPS) with Day-0 support across transformers, vLLM, SGLang, and llama.cpp.
Related event: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from Models
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- LMArena launches Agent Arena and Code Arena leaderboards for model comparison — arena · 2026-10-16
- Third-party tests find NVIDIA Nemotron-3.5 Bolt underperforms nano on pandas/numpy and decision-making tasks — norenEnmotalen · 2026-10-16
- Reflection open-sources Beam under Apache 2.0 with 40+ partner ecosystem — bhutanisanyam1 · 2026-10-16
- One Prompt, 629 Lines: IQuest-Q1 Builds a Deep-Sea Submarine Game in 2 Minutes — Div_pradeep · 2026-10-16