LFM3-VL-2B, compiled for the browser

Liquid AI's LFM3-VL-2B compiled into a fusor-ai bundle: the weights the browser runtime of liquidai-lmf3-wasm loads to hold a conversation about images on the device's CPU. Try it in the Space fusorlabs/liquidai-lmf3-wasm.

Source: LiquidAI/LFM3-VL-2B at revision f83d2b0a2296aaa277f394990a9b8b949ddf9691, compiled with the q7 profile: every large matrix 7-bit but the patch embedding, kept in f32.
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).

Model tree for fusorlabs/lfm3-vl-2b-web

Base model

Finetuned

Finetuned

(3)

this model