Thinking Machines Lab 发布 Inkling 2 Mini(26B/A3B)开源模型,主打本地部署编程
Thinking Machines Lab 这次的 Inkling 2 Mini 只有 26B 总参数、激活 3B,普通本地机器就能跑。transformers、llama.cpp 和 MLX 都已同步支持,Mac 用户用 MLX 直接上手,想在本地跑编程助手的可以试试和 Qwen3 对比一下。
Thinking Machines Lab 发布 Inkling 2 Mini,采用 A3B/26B 规模,官方强调其体积适合本地部署。Hugging Face 的 merve 在实测后称其编程表现令人满意,是一名的编码助手。
Inkling 2 Mini 已获得 transformers、llama.cpp 和 MLX 三套推理框架的官方支持,开发者可直接在本地环境跑通。MoE 架构(26B 总参数、3B 激活参数)让它在消费级硬件上也能保持较低推理成本,适合本地编程辅助场景。
对比 Qwen3 等同尺寸级开源模型,Inkling 2 Mini 的差异化卖点集中在代码能力与易部署性上。对想在本地搭建编程助手的开发者来说,llama.cpp 和 MLX 的即时支持意味着 Mac 用户也能无门槛体验。
🔥 Thinking Machines Lab dropped Inkling 2 Mini (A3B/26B), amazing size for your local setup
We had vibe-tested it to bits and pieces, it's an amazing coding companion, so we ship support for it in transformers, llama.cpp and MLX
Read our blog https://t.co/vwcCTu476q https://t.co/XANeMvFhSA
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Inkling 2 Mini, Thinking Machines Lab, llama.cpp, MLX.
Source attribution: curated from Merve Noyan (@mervenoyann). Cross-source corroboration: 6 independent sources have covered this development (including kimmonismus, Artificial Analysis, Thinking Machines Lab), confirming industry-wide signal strength.