llamaperf
Submit

Qwen3.6 27B

on AMD RX 7900 XTX · 32,768 ctx

Tone: mixedAMD hardware
May 4, 2026
Share
Throughput
32.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q6 (GGUF)
VRAM reported
24 GB

Use cases

coding

Summary

User is considering adding a second 7900 XTX for 48 GB VRAM to run larger models. Currently runs Qwen 27B Q6 dense with 32K context at 32 t/s prompt processing. Main use case is coding via opencode.