llamaperf
Submit

Qwen3.6 27B

on 2× AMD RX 9070 · llama.cpp · 131,072 ctx

Tone: positiveAMD hardware
May 21, 2026
Share
Throughput
46.9 t/s gen · 398.4 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
UD-Q5_K_XL (GGUF)
Flash Attention
on
MTP (Multi-Token Prediction)
on

Use cases

codingagentic

Summary

User reports generation around 45-52 t/s on two RX 9070 XTs with ROCm. Setup is MTP with spec-type = draft-mtp and spec-draft-n-max = 2, using the unsloth UD-Q5_K_XL GGUF. Prompt t/s varies, and draft acceptance rate is around 0.8-0.99. User praises the speed, smarts and steerability for agentic coding tasks.
View source ↗