ITHome · AI·· 9 days ago
Taobao MNN team open-sources 0.3B mobile model MNN-Pocket-0.3B
Brief overview
Taobao MNN team open-sources 0.3B mobile model MNN-Pocket-0.3B, achieving 350 tokens/s on real iPhone 18 Pro offline. The model's peak memory is below 300MB, decoding throughput exceeds 200 tokens/s, INT4 deployment file is 173MB, English IFEval score is 73.20, and Chinese instruction following IFEval-zh score is 74.59.
Source: ITHome · AI · ithome.com