Probably one of cheapest and performant local setups you can get ( ~ 1600€ )
i7-14700KF , 64 GB RAM Radeon RX 9070XT 16GB github.com/niko1221/strata for inference Qwen3.8-Flash-Next-GSQ-RCO-Q2_0 model Runs at 90-70 tokens/sec :)
参与讨论
i7-14700KF , 64 GB RAM Radeon RX 9070XT 16GB github.com/niko1221/strata for inference Qwen3.8-Flash-Next-GSQ-RCO-Q2_0 model Runs at 90-70 tokens/sec :)