Try LFM • Docs • LEAP • Discord 🇯🇵 LFM2.5 1.2B JP 202606 ONNX ONNX export of LFM2.5 1.2B JP 202606 for cross platform deployment via ONNX Runtime, Transformers.js, and the WebGPU stack. Same weights, same chat template — just compiled into ONNX graphs at multiple precisions, including a WebGPU friendly INT4 + FP16 mix. LiquidAI/LFM2.5 1.2B JP 202606 は当社の汎用日本語チャットモデルです。本リポジトリはその ONNX エクスポートで、ONNX Runtime / Transformers.js / WebGPU での実行に対応しています。重みおよびチャットテンプレートは同一です。 📦 Files File Format Embedding Weights Cache / activations Approx. size onnx/model.onnx FP32 FP32 FP32 FP32 4.7 GB onnx/model fp16.onnx FP16 FP16 FP16 FP16 2.4 GB onnx/model q4.onnx INT4 INT4 ( GatherBlockQuantized ) INT4 ( MatMulNBits ) FP32 834 MB onnx/model q4f16.onnx INT4 + FP16 INT4 + FP16 scales INT4 + FP16 scales FP16 744 MB onnx/model q4f32.onnx INT4 (MatMul only) FP32 (kept) INT4 ( MatMulNBits ) FP32 1.2 GB onnx/model q8.onnx INT8 (MatMul only) FP32 (kept) INT8 ( MatMulNBits ) FP32 1.8 GB model q4f16.onnx is the recommended variant for WebGPU : INT4 weights with FP16 scales, FP16 KV cache and conv state I/O, FP32 logits via an inserted Cast — the format Transformers.js targets for browser inference. Each .onnx…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy