🖼️00Read later0Read MoreShapeLearn-Lite Held Up. ShapeLearn Did Better: Qwen 3.8 27BHacker News·about 1 month ago#hfIHskmF#byteshape#modelacctpsbpw#modelkldsize#modelaccntp#qwen+5 more🧰Tag tools✨Add tagByteShape's full ShapeLearn release of Qwen 3.8 27B: five GGUF models on the measured quality-speed frontier across six GPUs, plus MTP and DFlash2 speculative decoding.15s
