Qwen3-Coder 30B (3B active)
on AMD Radeon 8060S integrated GPU (Strix Halo, gfx1151) · 1bit engine / llama.cpp (Vulkan 7fe450e)
Summary
User reports Qwen3-Coder 30B-A3B at 84.7 t/s generation and 1297 t/s prompt processing on one Strix Halo integrated GPU.
Setup is llama.cpp Vulkan pin 7fe450e with Unsloth Dynamic UD-Q4_K_XL GGUF, 124 GB unified memory visible to the backend.
The figures are separate synthetic llama-bench pp512 and tg128 phases, not client TTFT or end-to-end throughput; total context capacity is unspecified.
Compare this run
Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.
Qwen3-Coder 30B · 3B active at 4-bit by hardware
- 107.0 t/s · one run
- 70.3 t/s · 2 runs
- 69.9 t/s · 6 runs
- 66.1 t/s · one run
Bars are medians on one scale, 0 to 107.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.