# Inkling-2-Small

> Inkling 2 Small is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

- **Organisation:** thinkingmachines
- **Category:** Vision-Language Models
- **Parameters:** 383B
- **Context length:** 1,048,576 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-11-04
- **Hugging Face:** 45.4K downloads (30 days), 634 likes
- **Ollama:** `ollama run inkling-2-small`

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 125.15 |
| Q3_K_M | 185.09 |
| Q4_K_M | 229.1 |
| Q5_K_M | 268.44 |
| Q6_K | 310.58 |
| Q8_0 | 400.02 |
| F16 | 751.21 |

## Runs with

- [Ollama](https://selfhost.directory/project/ollama)
- [Transformers](https://github.com/huggingface/transformers)

## About

Inkling 2 Small is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and visual tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.

Languages: English, with general multilingual capabilities across other languages.

Try Inkling 2 Small on the Tinker Playground or access via API using the Tinker Cookbook. To fine-tune Inkling 2 Small with Tinker, also install the tml-renderers package.

Inkling 2 Small supports local inference using:

• SGLang (recipe)
• vLLM (recipe)
• TokenSpeed (recipe)
• Unsloth (recipe)

Inkling 2 Small can also be post-trained with:

• Miles
• SkyRL
• Snowflake Cortex Training

API access is also available through third party inference providers, including:

• NVIDIA
• Fireworks
• Together
• Baseten
• Nebius
• Modal
• Cloudflare

The model is distributed in two checkpoint formats.

## Alternatives

- [zai-org/GLM-5.3-Flash](https://selfhost.directory/models/zai-org/glm-5.3-flash) (321B (18.3B active), MIT, ≈213.49 GB at Q4): 👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.
- [Qwen/Qwen3.5-397B-A17B](https://selfhost.directory/models/qwen/qwen3.5-397b-a17b) (403B (17B active), Apache 2.0, ≈240.59 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [MiniMaxAI/MiniMax-M3](https://selfhost.directory/models/minimaxai/minimax-m3) (427B, minimax-community, ≈254.61 GB at Q4): MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.
- [thinkingmachines/Inkling-Small](https://selfhost.directory/models/thinkingmachines/inkling-small) (266B (1.7B active), Apache 2.0, ≈159.48 GB at Q4): Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.
- [zai-org/GLM-5.3-Flash-BF16](https://selfhost.directory/models/zai-org/glm-5.3-flash-bf16) (321B (18.3B active), MIT, ≈213.49 GB at Q4): 👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.
- [deepseek-ai/DeepSeek-V4-Flash-Vision-Exp](https://selfhost.directory/models/deepseek-ai/deepseek-v4-flash-vision-exp) (305B (15.2B active), MIT, ≈181.78 GB at Q4): We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

More: https://selfhost.directory/models/thinkingmachines/inkling-2-small/alternatives

## Runs well on

- [Apple M3 Ultra (512 GB)](https://selfhost.directory/models/thinkingmachines/inkling-2-small/on/apple-m3-ultra-512gb): Q6_K, est. 1.4 tok/s

## Similar size

- [zai-org/GLM-5.3-Flash](https://selfhost.directory/models/zai-org/glm-5.3-flash) (321B)
- [MiniMaxAI/MiniMax-M3](https://selfhost.directory/models/minimaxai/minimax-m3) (427B)
- [Qwen/Qwen3.5-397B-A17B](https://selfhost.directory/models/qwen/qwen3.5-397b-a17b) (403B)
- [deepseek-ai/DeepSeek-V4-Flash-Vision-Exp](https://selfhost.directory/models/deepseek-ai/deepseek-v4-flash-vision-exp) (305B)
- [meta-llama/Llama-4-Maverick-17B-128E-Instruct](https://selfhost.directory/models/meta-llama/llama-4-maverick-17b-128e-instruct) (402B)
- [zai-org/GLM-5.3-Flash-BF16](https://selfhost.directory/models/zai-org/glm-5.3-flash-bf16) (321B)

## FAQ

**How much VRAM does Inkling-2-Small need?**
About 229 GB at Q4_K_M with an 8K context. Q8_0 needs about 400 GB and full precision about 751 GB. Longer contexts need more memory for the KV cache.

**Can Inkling-2-Small run on the Apple M3 Ultra (512 GB)?**
Yes. It fits at Q6_K (about 311 GB), at an estimated 1.4 tokens/s.

**Can I use Inkling-2-Small commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of Inkling-2-Small?**
1,048,576 tokens (1M). The full window needs far more memory than an 8K context.

**How do I run Inkling-2-Small with Ollama?**
Run ollama run inkling-2-small in a terminal.

## Links

- huggingface: https://huggingface.co/thinkingmachines/Inkling-2-Small
- github: https://github.com/thinking-machines-lab/tinker-cookbook
- demo: https://tinker.thinkingmachines.ai/playground
- ollama: https://ollama.com/library/inkling-2-small

---
Source: https://selfhost.directory/models/thinkingmachines/inkling-2-small