llamaperf
Submit

Qwen3.8 27B

on 2× NVIDIA RTX 3090

Tone: positiveNVIDIA hardware
Aug 28, 2026
Share
Throughput
60-63 t/s gen
Quant
Q6 (GGUF)

Use cases

agenticcoding

Summary

User reports Qwen3.8-27B Q6 at 60-63 t/s on dual GPUs (RTX 3090 + RTX 3060). The run covered 20 hours of agentic coding.
View source ↗