Qwen3 8B
on NVIDIA RTX 5090 · llama.cpp · 8,192 ctx
Use cases
summarizationmultilingual
Summary
User benchmarks a DSpark PC Tree speculative decoding fork at 159.00 tok/s in its best config, PCTree k3/n16, against 94.27 tok/s for plain decoding.
User also tests Qwen3.8 27B Q4, with worse results.