Qwen3.8 27B
on AMD Gorgon Halo 192GB · llama.cpp
Use cases
agenticlong-context
Summary
User benchmarks Qwen3.8 27B (dense) at 9 t/s generation and 463 t/s prompt reading on a MINISFORUM MS-S1 MAX P495 (Ryzen AI Max+ PRO 495, 192GB) at empty context.
Setup is llama.cpp build 23f7aab with Vulkan, Q6_K_XL weights, q8_0 KV cache and flash attention, ubatch 512, all layers on the GPU.
With MTP speculative decoding (--spec-type draft-mtp) the same model reaches 24 t/s with 82.9% draft acceptance. At 32k context it reads at 286 t/s and writes at 9 t/s; at 128k, 131 t/s and 8 t/s. The user could not reproduce an f16 KV collapse at depth and says the machine is not worth $8k.