Qwen3 8B
on AMD RX 7900 GRE 16GB · llama.cpp
Summary
User benchmarks Qwen3-8B Q8_0 with DSpark speculative decoding in llama.cpp on an RX 7900 GRE 16GB, reaching 133 t/s on ROCm versus 59 t/s without speculation, and 115 t/s versus 62 t/s on Vulkan.
Setup is llama.cpp with Q8_0 weights, greedy decoding, one user and 32 prompts per setting.
DFlash gave 1.5-1.9x, a 0.6B draft model about 1.3x, and n-gram lookup did nothing. The best number of guessed tokens is 3 on Vulkan and 7 on ROCm, and prompt processing is about 8% slower with DSpark loaded. Only 5-6 of 16 answers matched normal decoding word for word.