Qwen3.8 runs locally at 51 t/s on 12GB laptop GPU

A user reports that the Strata inference engine with ISTA-DASLab's quantized Qwen3.8-Flash-Next hits 51 t/s generation and 1500 t/s prompt processing on a 12GB VRAM, 64GB RAM laptop, far outpacing stock llama.cpp. Strata currently supports only Nvidia and select GGUF models.

• Qwen3.8-Flash-Next Hits 65 Tokens/Second on 12GB VRAM2026-09-24
• Qwen3.8 27B IQ3_XXS vs Bonsai Ternary PQ2 quantization test2026-09-20
• Trump's 'super intelligence' accord includes spelling error2026-10-01
• BAAI Releases AREX-2: 27B Long-Horizon Agent Model2026-10-01
• Meta Dodges Billions in US Taxes by Calling AI Data Centers Experiments2026-09-30