Shapelearn Qwen 3.8 27B (13.1 GB VRAM)

Shapelearn's Qwen 3.8 27B model, requiring 13.1 GB VRAM, was evaluated on RTX Pro 6000 and RTX 4080 GPUs against competing quantization methods. Data compared various models like ByteShape, Unsloth, ISTA-DASLab, Bartowski, and AtomicChat for accuracy (Acc), tokens per second (TPS), and bits per weight (BPW). For instance, on the RTX Pro 6000, ByteShape's IQ4_XS-3.84bpw achieved 0.9963 accuracy and 90.42 TPS, while on the RTX 4080, it reached 0.9963 accuracy and 45.74 TPS.