Inkling 2 Mini lands on Ollama, runs locally in 16GB of RAM
Thinking Machines 发布的 Apache 2.0 开源模型 Inkling 2 Mini 已上架 Ollama(0.40.17 预发布版),可完全本地运行,成为近期本地部署圈的关注焦点。该模型采用循环 transformer MoE 架构(部分层对每个 token 多次循环),总参数 26.4B、激活参数 5.4B(含循环),另有帖子提到在 Mac mini 实测中仅激活 3.4B。
已确认
- 模型以 Apache 2.0 许可开源,架构为循环 transformer MoE,总参数 26.4B、激活参数 5.4B(含循环)
- Ollama 模型页提供 latest、26b-a5b 及 MLX 版 26b-a5b-nvfp4 三个 tag,均约 20GB,支持文本+图像输入,并可通过一条命令接入编码 Agent
- 模型小到可在 32GB+ 内存的 Mac 上运行;Unsloth 发布 GGUF 量化与本地运行指南,称 26.4B MoE 仅需 16GB 内存即可跑通
- 在 DeepSWE 编码基准上成绩为同级最强(据 Unsloth 相关转述)
- 已有开发者拿到早期访问权限后,在一台 Mac mini 上用 Ollama 部署该模型,结合 OpenJarvisAI 实现日程安排等个人 AI 助手功能,完全本地运行
为什么重要
- 循环 transformer 架构让小激活参数实现较强能力,显著降低本地部署门槛,16GB 内存的消费级设备即可运行 26B 级模型
- Apache 2.0 开源加 Ollama 一条命令接入编码 Agent,为个人完全本地化 AI 助手提供了低门槛方案
2026-11-21 ~ 2026-11-21 · 5 related posts
- Episode 1: Thinking Machines Launches Inkling 2 Small, Weights to Open-Source Next Week(2026-11-06, 101 posts)
- Episode 2: Inkling 2 Small generates full stock diligence memo for $0.69(2026-11-06, 2 posts)
- Episode 3: Inkling 2 Small tops US open-weight model rankings(2026-11-06, 2 posts)
- Episode 4: Ex-OpenAI Policy Chief Miles Brundage Praises Inkling 2 Small(2026-11-06, 2 posts)
- Episode 5: Inkling 2 Small Pushes Open-Model Frontier in Code and Finance(2026-11-07, 2 posts)
- Episode 6: Leaks claim Thinky's new model matches DeepSeek at a fraction of the cost(2026-11-07, 2 posts)
- Episode 7: Inkling 2 Small Architecture Revealed: 594B Params, 17B Active(2026-11-08, 2 posts)
- Episode 8: Thinking Machines Offers Inkling 2 Small Free on OpenCode(2026-11-08, 4 posts)
- Episode 9: Thinking Machines Releases Inkling 2 Small with Open Weights Coming(2026-11-09, 3 posts)
- Episode 10: Thinking Machines Launches Inkling 2 Small on OpenRouter(2026-11-10, 2 posts)
- Episode 11: Thinking Machines Lab Open-Sources 26B Looped Transformer Inkling 2 Mini(2026-11-21, 51 posts)
- Episode 12: Inkling 2 Mini lands on Ollama, runs locally in 16GB of RAM(2026-11-21, 5 posts)
- Episode 13: Thinking Machines Open-Sources Inkling 2 Mini: 5.4B Active Params Rival 27B-Class Models(2026-11-21, 7 posts)
Primary sources
- Inkling 2 Mini runs locally in 16GB RAM: 5.4B-active MoE tops its size class — simonguozirui · 2026-11-21
- Inkling 2 Mini runs a local Mac assistant: 26.4B params, only 3.4B active — simonguozirui · 2026-11-21
- [source] Inkling 2 Mini on Ollama: MLX build, one-command hooks into Claude Code and OpenCode — ollama · 2026-11-21
- Thinky Machines' Inkling 2 Mini lands on Ollama: 5.4B active params, loops middle layers 3x, runs on 32GB Macs — simonguozirui · 2026-11-21
- Inkling-2-Mini: Thinking Machines' 26.4B looped-transformer MoE runs in 16GB RAM — simonguozirui · 2026-11-21