CoolFace
Modelpublic

magiccodingman/Jasper-Token-Compression-600M-ONNX-FP32

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
0likes26downloads
Model Card

Jasper Token Compression 600M — ONNX FP32

ONNX export of infgrad/Jasper-Token-Compression-600M.

Precision: FP32 Quantization: None (FP32) Model size: 2.26 GiB

Full-precision FP32 ONNX export. This is the reference model used for the included quantization fidelity comparisons.

Benchmarks

TokensMedian latencyTokens/s
32139.282 ms229.7
128155.466 ms823.3
512211.763 ms2,417.8
1024288.388 ms3,550.8

Attribution

Original model: infgrad/Jasper-Token-Compression-600M