# Thinking Machines Lab 发布 Inkling 开源模型

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-07-16 06:17
- AIHOT 分数：59
- AIHOT 链接：https://aihot.virxact.com/items/cmrmnm0nk06mwbiul1j0eaunz
- 原文链接：https://x.com/rohanpaul_ai/status/2077517932750577711

## AI 摘要

Thinking Machines Lab 发布首个开源权重模型 Inkling，975B 参数（41B 激活），支持多模态推理与可调节推理努力度。模型拥有 1M token 上下文窗口，在 Terminal Bench 上以约三分之一的 token 量匹配 Nemotron 3 Ultra。Inkling 支持微调，完整权重已上架 Hugging Face。

## 正文

Mira Murati's Thinking Machines Lab released Inkling， its first open-weights model.

A 975B-parameter （41B active） open-weights model with multimodal reasoning and adjustable effort.

- A 1M-token context window lets the system process unusually long documents and workflows.

- Trained on 45T tokens spanning text， images， audio， and video from scratch.

- Users can raise reasoning effort for difficult tasks or reduce it for speed.

- The release matched Nemotron 3 Ultra on Terminal Bench using roughly one-third as many tokens.

- Strong Native audio and vision processing. Inkling scored 91.4% on VoiceBench and 82.0% on CharXiv RQ with Python.

- Large-scale reinforcement learning used more than 30M rollouts and steadily improved reasoning scores.

Fine-tuning support arrives through Tinker， while full weights are available through Hugging Face.

Inkling-Small activates 12B parameters and sometimes matches its larger sibling on core evaluations.

Thinking Machines Lab's latest valuation was at $12B， following a $2B seed round. Nvidia later invested an undisclosed amount， while reported $50B talks never produced a confirmed valuation.

### 引用推文

> Mira Murati：Our first model, Inkling. Trained from scratch, weights are open, fine-tunable on Tinker today.