Qwen3-Coder 30B (3B active)
AMD Radeon 8060S integrated GPU (Strix Halo, gfx1151) · 1bit engine / llama.cpp (Vulkan 7fe450e)
- generation:
- 84.7 tokens/s
- prompt processing (prefill):
- 1297.0 tokens/s
- quant:
- UD-Q4_K_XL (GGUF)
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.