Qwen3.8 27B Swift-1.5
on NVIDIA RTX 3090 · 150,000 ctx
Summary
User benchmarks Swift 1.5 + HyperQwen at 104.0 tok/s decode on an RTX 3090 24GB.
Setup uses FP8 KV cache and 150k configured context, with speculative decoding via MTP and a Swift-specific 65,536-token draft vocabulary.
Swift 1.5 INT4 heads achieves roughly 37% lower average time per task than the HyperQwen fast quant, averaging 68.2 s and 5,669 output tokens per task versus 108.1 s and 8,985 tokens. The HyperQwen fast quant decodes at 112.1 tok/s, Swift 1.0 at 105.9 tok/s, and Swift 1.5 INT8 heads at 104.0 tok/s. Average task time covers about 630 tasks.