14.3 t/s gen · 364.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q5_K_P (GGUF)
KV cache
Q4
Summary
User benchmarks Qwen3.8-27B and Gemma4-26B-A4B on an AMD V620 using llama.cpp with ROCm and Vulkan.
Qwen results are shown; Gemma results appear in a table but are not extracted as the primary model.