Qwen3.8 27B

on 2× AMD Radeon AI PRO R9700 32GB · vLLM

Sep 7, 2026

Throughput

75.2 t/s gen · 671.9 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

FP8

KV cache

F16

System RAM

64 GB

VRAM reported

32 GB

Summary

User benchmarks dual R9700 GPUs with tensor parallelism, comparing PCIe gen4 x16+x4 against gen5 x8/x8. Setup is vLLM with stilldeadcode/vllm-radiance:0.7.4 on a 9950X with 64GB DDR5 6000. The gen5 x8/x8 configuration shows 18-32% improvements, with results given for concurrency 1, 2, and 4.

View source ↗