Qwen3.8 27B L0xRE
on NVIDIA RTX 3060 12GB · Beellama · 80,000 ctx
Use cases
codingagentic
Summary
User reports Qwen3.8-27B at 40 t/s on an RTX 3060 12GB.
Setup is Beellama with an IQ3 head and KvarnN KV quantization at 3/3, 80k context, and Dflash2 speculative decoding.
The model is a custom hybrid combining Escha Labs W2 body with a Lowgpu IQ3 head, 8.65GB total size. User also tested on a 4070 Ti and 50-series cards.