Liquid AI 发布 LFM3 小模型家族及 d1 决策模型 v0.40.12

v0.40.12

要点速览

Liquid AI 发布 LFM3 小模型家族，包含 1.7B 参数的 lfm3 文本模型（256K token 上下文）、支持图像理解的 lfm3-vl、18 语言语音处理能力的 lfm3-audio 及通用模型 lfm3-omni，用于本地智能体和结构化输出；d1 决策模型升级至 2B 参数，支持文本、图像及音频决策，部分模型支持苹果硬件。

正文

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