2026-09-29 · America/Los_Angeles · 社区动态 · #6

Qwen3.8 flash next ISTA-DASLab GGUF 50t/s TG and 1500t/s PP with 12GB VRAM and 64GB RAM Laptop on 'Strata' engine

I think most people are sleeping on this inference engine. I tried multiple llama.cpp forks and none of them comes close to the inference speed of Strata. Initial version had some bugs with kv cache, cpu throttling and the developer fixed them. Inference engine (only runs on Nvidia for now; AMD support is experimental): https://github.com/Niko1221/Strata Here are some metrics with screenshots. My laptop has 5070ti 12GB VRAM, 64GB ddr5 RAM, Intel 275HX CPU, gen4 SSD. Aquarium test (unsloth studio connected via local API) The model I used was…

热度 49.5 / 100；排名与评分保留该期记录。