Liquid AI LFM3
LFM3 是 Liquid AI 全新推出的小型模型系列，基於 Liquid 全新的三混合架構建置，面向本地智慧體、工具呼叫和結構化輸出。該系列包括：
- lfm3：一個 1.7B 引數的文字模型，具有 256K token 的上下文視窗
- lfm3-vl：增加了影像理解能力
- lfm3-audio：支援 18 種語言的語音識別、翻譯和文字轉語音
- lfm3-omni：將文字、影像和音訊整合於一個模型
ollama run lfm3
d1 決策模型
Liquid AI 的 d1 模型現已推出 2B 規模版本，基於 LFM3 建置。d1 針對文字和影像做出決策，而 d1-omni 增加了音訊能力。
ollama run d1:2b " I was charged twice for order 4417. " --ask " Is this a billing issue? "
注意：本次發布中，lfm3 和 d1 2b 已在 Apple 硬體上獲得支援。對 Linux/Windows 的支援即將推出。
變更內容
在 Apple 晶片上，Gemma 4、Flint 和 Laguna 模型的提示處理速度更快
推測解碼現已在 MLX 上支援 DFlash2 草稿模型
Gemma 4 在小尺寸影像中保留更多細節
ollama launch 現已相容 OpenCode v2
修復了來自 Kimi CLI 的純工具助手輪次
更新了 MLX 和 llama.cpp
完整變更日誌：v0.40.11...v0.40.12
由 AI 翻譯，以原文為準。
原文
Liquid AI LFM3
LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. The family includes:
lfm3 : a 1.7B text model with a 256K-token context window
lfm3-vl : adds image understanding
lfm3-audio : speech recognition, translation, and text-to-speech in 18 languages
lfm3-omni : text, images, and audio in one model
ollama run lfm3
d1 decision models
Liquid AI's d1 models now come in a 2B size, built on LFM3. d1 makes decisions about text and images, and d1-omni adds audio.
ollama run d1:2b " I was charged twice for order 4417. " --ask " Is this a billing issue? "
Note: lfm3 and d1 2b are supported on Apple hardware in this release. Support for Linux/Windows coming soon.
What's Changed
Faster prompt processing on Apple silicon for Gemma 4, Flint and Laguna models
Speculative decoding now supports DFlash2 draft models on MLX
Gemma 4 keeps more detail in small images
ollama launch now works with OpenCode v2
Fixed tool-only assistant turns from Kimi CLI
Updated MLX and llama.cpp
Full Changelog : v0.40.11...v0.40.12