llamaperf

Qwen3-Coder 30B (3B active)

on AMD Ryzen AI Max+ 395 / Radeon 8060S (Framework Desktop; 64 GB unified) · llama.cpp

Oct 13, 2026
Throughput
69.2 t/s gen · 1242.4 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
UD-Q6_K_XL (GGUF)
KV cache
F16
Flash Attention
on
MTP (Multi-Token Prediction)
off
System RAM
64 GB

Summary

User reports Qwen3-Coder-30B-A3B-Instruct at 69.2 t/s generation and 1242.4 t/s prompt processing on a Framework Desktop with AMD Ryzen AI Max+ 395 and Radeon 8060S, 64 GB unified memory. Setup is llama.cpp with UD-Q6_K_XL, f16 K/V cache, flash attention, one Vulkan device and 99 GPU layers. The two figures are separate depth-0 arms, PP512 and TG32, not one 512-input/32-output run.

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

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.

Every Qwen3-Coder report →