llamaperf
Submit

Qwen3.6 27B

on NVIDIA RTX 3060 12GB · llama.cpp · 32,000 ctx

Tone: positiveNVIDIA hardware
May 12, 2026
Throughput
70.0 t/s gen · 780.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q2-XS (GGUF)
KV cache
Q8
Flash Attention
off
Rating
4/5
System RAM
32 GB
VRAM reported
12 GB

Use cases

codingcreative-writingtool-usesummarizationvisionagenticmultilingual

Summary

User reports a dense model at 11.9 GB GGUF size, barely offloading to CPU. The user wants to try a higher quant, having chosen this one because of the 11.9 GB GGUF size.