# Inkling-Small

> A quarter of Inkling's size, comparable performance, and 3x cheaper output — 276B / 12B-active Apache-2.0 MoE released July 30, 2026.

- Maker: Thinking Machines Lab
- Line: Inkling
- Canonical page: https://ai-tldr.dev/models/inkling-small/
- Updated: 2026-08-02

## In short

Inkling-Small is Thinking Machines Lab's efficient sibling to Inkling, released on July 30, 2026 as an Apache-2.0 open-weights model. It has a 1M-token context window. You can use it through Tinker (Thinking Machines) and Together AI.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 1M | [1] |
| Licence | Apache-2.0 · open weights | [1] |
| Released | 30 July 2026 | [2] |
| Parameters | 276B total · 12B active | [1] |

## Sources

1. [Inkling-Small model card](https://thinkingmachines.ai/model-card/inkling-small/)
2. [Thinking Machines Lab](https://thinkingmachines.ai/)

## Overview

Inkling-Small is Thinking Machines Lab's efficient sibling to Inkling, released on July 30, 2026 as an Apache-2.0 open-weights model. It is a sparse Mixture-of-Experts transformer with 276 billion total parameters and 12 billion active per token — about a quarter of Inkling's size — and Thinking Machines says it "matches or exceeds Inkling on reasoning and agentic tasks" while trailing on knowledge coverage and factuality.

The model keeps Inkling's design choices: a 42-layer decoder-only transformer with 256 routed experts plus 2 shared experts (6 active per token), hybrid local and global attention, native reasoning over text, images, and audio through an encoder-free architecture with a light-weight embedding layer, variable thinking effort, and a context window of up to 1 million tokens. BF16 and NVFP4 (Blackwell-tuned) checkpoints are both published, so Inkling-Small runs on much smaller boxes — the NVFP4 build fits in a single NVIDIA B300 or two H200 GPUs (~180 GB VRAM), versus the ~600 GB the BF16 Inkling checkpoint needs.

Full weights are on Hugging Face under Apache-2.0. Inkling-Small is served on the Tinker inference platform "with a limited-time discount" (Tinker output pricing is $1.20 per 1M tokens versus $4.05 for Inkling) and is exposed for chat over text, image, and audio through the Tinker Playground. Together AI lists it as an inference provider on the Hugging Face page.

## Benchmarks

- AIME 2026: 95.5% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- GPQA Diamond: 89.5% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- HMMT Feb 2026: 90.2% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- SWE-Bench Verified: 80.2% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- Terminal Bench 2.1: 64.7% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- HLE (text only): 31.6% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- HLE (with tools): 47.8% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- MMMU Pro (Standard 10): 74% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- VoiceBench: 90.1% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- IFBench: 82.2% ([source](https://thinkingmachines.ai/model-card/inkling-small/))
- Global-MMLU-Lite: 86.7% ([source](https://thinkingmachines.ai/model-card/inkling-small/))

## Pricing

- Output: $1.20 / 1M tokens

Output-token pricing on Tinker with a limited-time launch discount; Inkling output is $4.05 per 1M tokens on the same platform.

Source: https://thinkingmachines.ai/news/inkling-small/

## Strengths

- Open Apache-2.0 weights, downloadable and commercially usable, at roughly a quarter of Inkling's size
- Matches or exceeds Inkling on reasoning and agentic-coding benchmarks despite the smaller footprint
- Native multimodal input (text, image, audio) with a 1M-token context and variable thinking effort
- NVFP4 checkpoint fits on a single Blackwell B300 or two H200 GPUs — much cheaper to self-host than Inkling
- $1.20 per 1M output tokens on Tinker with a limited-time discount, vs $4.05 for Inkling

## Best for

- Reach for it as an open-weight base to fine-tune for a domain, product, or private data on Tinker without renting an Inkling-scale cluster.
- Reach for it when you want native multimodal input (text + image + audio) with a 1M-token context at a lower cost tier.
- Reach for it when a permissive Apache-2.0 license, smaller GPU budget, and self-hostable weights are hard requirements.

## How to access

- [Tinker (Thinking Machines)](https://tinker-docs.thinkingmachines.ai/tinker/)
- [Together AI](https://www.together.ai/)

## Inkling versions

- Inkling-Small (30 July 2026): Efficient 276B / 12B-active sibling — comparable performance to Inkling at a quarter of the size, 3x cheaper output on Tinker. — this page
- [Inkling](https://ai-tldr.dev/models/inkling/) (15 July 2026): First release — 975B / 41B-active MoE, Apache-2.0.

## FAQ

### What is Inkling-Small?

Inkling-Small is Thinking Machines Lab's efficient open-weights sibling to Inkling, released on July 30, 2026 under Apache-2.0. It is a 276B total / 12B active sparse Mixture-of-Experts transformer with a 1M-token context and native text, image, and audio input — about a quarter of Inkling's size, with comparable performance.

### How does Inkling-Small compare to Inkling?

Thinking Machines says Inkling-Small "matches or exceeds Inkling on reasoning and agentic tasks." On the published model card it beats Inkling on SWE-Bench Verified (80.2 vs 77.6), Terminal Bench 2.1 (64.7 vs 63.8), and HLE text-only (31.6 vs 29.7), while Inkling keeps an edge on knowledge coverage and factuality (SimpleQA Verified 43.9 vs 20.6). Inkling-Small is a quarter of Inkling's active-parameter footprint (12B vs 41B) and 3x cheaper per output token on Tinker.

### What license does Inkling-Small use?

Inkling-Small is published under Apache-2.0. The BF16 and NVFP4 (NVIDIA Blackwell-tuned) checkpoints are both on Hugging Face at thinkingmachines/Inkling-Small and thinkingmachines/Inkling-Small-NVFP4 and can be downloaded, fine-tuned, and used commercially without extra restrictions.

### What hardware do I need to run Inkling-Small?

The BF16 checkpoint needs roughly 600 GB of aggregated GPU VRAM (about 4x NVIDIA B300 or 8x H200 GPUs per Thinking Machines' model card). The NVFP4 build is much smaller — around 180 GB — and fits on a single B300 (W4A4) or 2x H200 GPUs (W4A16).

### How much does Inkling-Small cost on Tinker?

Thinking Machines lists Inkling-Small output pricing at $1.20 per 1M tokens on Tinker with a limited-time launch discount, compared to $4.05 per 1M tokens for Inkling on the same platform.

## Links

- [Inkling-Small announcement](https://thinkingmachines.ai/news/inkling-small/)
- [Inkling-Small model card](https://thinkingmachines.ai/model-card/inkling-small/)
- [Inkling-Small weights on Hugging Face](https://huggingface.co/thinkingmachines/Inkling-Small)
- [Inkling-Small-NVFP4 checkpoint on Hugging Face](https://huggingface.co/thinkingmachines/Inkling-Small-NVFP4)
- [Tinker documentation](https://tinker-docs.thinkingmachines.ai/tinker/)
- [Thinking Machines Lab](https://thinkingmachines.ai/)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/inkling-small/