fusorlabs/lfm3-omni-2b-web

LFM3-Omni-2B, compiled for the browser

Liquid AI's LFM3-Omni-2B compiled into a fusor-ai bundle: the weights the browser runtime of liquidai-lmf3-wasm loads to read images, hear speech, transcribe it, speak and hold a conversation in text and speech on the device's CPU. Try it in the Space fusorlabs/liquidai-lmf3-wasm.

• Source: LiquidAI/LFM3-Omni-2B at revision ce2458cbce4ad970f92032ed94e3d18d30b04f9c, compiled with the q7 profile: every large matrix 7-bit but the patch embedding and the audio subsampler's, kept in f32; with the speech codec's decoder.
• Format: manifest.json lists every tensor and part; each part is named by its BLAKE3 hash, which the runtime checks as it loads.
• Reproduce it: just model in liquidai-lmf3-wasm downloads the checkpoint and compiles the same bundle.

This is not a PyTorch or safetensors checkpoint: it only loads in the liquidai-lmf3-wasm runtime.

The model is under the LFM Open License v1.0 (LICENSE).