llamaperf

Qwen3.8 27B

on NVIDIA RTX 5060 Ti 16GB · 65,536 ctx

Tone: positiveNVIDIA hardware
Sep 7, 2026
Throughput
29.8 t/s gen
Quant
IQ3_XXS
KV cache
q8
MTP (Multi-Token Prediction)
on
VRAM reported
16 GB

Use cases

long-context

Summary

User reports a recommended single-card preset for Qwen3.8 27B on an RTX 5060 Ti 16GB, with sustained decode at 45.9K prompt tokens. Two retrieval and two sustained checks passed. User also mentions a 2x RTX 5060 Ti setup with the Q6_K quant at 131K context, reaching 38.6 t/s decode and 597.9 t/s prefill.