Model reference · open weights
LFM2.5-Audio-JP is an open-weight audio or speech model from LiquidAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" / LFM2.5-Audio-1.5B-JP This repository contains GGUF quantizations of LiquidAI/LFM2.5-Audio-1.5B-JP for use with llama.cpp. Available files Runners runners folder contains pre-built binaries for various architectures: - llama-liquid-audio-cli - llama-liquid-audio-server 🏃 How to run LFM2.5-Audio-JP CLI Set env variables. ASR (audio - text) TTS (text - audio) Interleaved (audio/text - audio + text) Server Start server Use liquidaudiochat.py script to communicate with the server. Source Code for Runners Runners are built from https://github.com/ggml-org/llama.cpp/pull/18641. 📬 Contact - Got questions or want to connect? Join our Discord community - If you are interested in custom solutions with edge deployment, please contact our sales team. License The code in this repository and associated weights are licensed under the LFM Open License v1.0. The code for the audio encoder is based on Nvidia NeMo, licensed under Apache 2.0, and the canary-180m-flash checkpoint, licensed under CC-BY 4.0. To simplify dependency resolution, we also ship the Python code of Kyutai Mimi, licensed under the MIT License. We also redistribute weights for Kyutai Mimi, licensed under CC-BY-4.0. Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | LiquidAI |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | llama.cpp |
| Based on | LiquidAI/LFM2.5-Audio-1.5B-JP |
| Released | 2026-05-27 |
| Popularity | 2k downloads / month |
| Likes | 31 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| LFM2.5-Audio-1.5B-JP-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys lfm2-5-audio-jp for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lfm2-5-audio-jp below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="lfm2-5-audio-jp" -F file=@audio.mp3
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗