Back to directory
Coding · 2026-09-14

Qwen Flash Next on a 12GB RTX 3500 Ada laptop

A laptop workflow combines Qwen Flash Next, llama.cpp and a DeepSeek harness, using system memory and SSD-backed loading to make a MoE model practical on 12GB of VRAM.

This contributor uses Qwen 3.8 Flash Next Q3 XXS for both hobby and professional projects on a laptop with an RTX 3500 Ada, 12GB of VRAM and 64GB of RAM. The runtime is llama.cpp and the surrounding workflow uses a DeepSeek harness. To achieve usable speed, the setup loads part of the MoE into CUDA-addressable system memory and keeps PLE data on an SSD, using lazy loading and a reduced load mode. The reported performance is around 10–15 tokens per second for generation and 80–120 tokens per second for prefill.

VERIFIABLE SOURCE

Submitted anonymously via Tally · reference zEOMJ20

View submission form