Tim

timbuksu

AI & ML interests

None yet

Recent Activity

new activity 30 days ago

turboderp/Qwen3.8-Flash-Next-exl3:Benchmarked 4.05 and 5.05 bpw on 1× RTX PRO 6000 Blackwell (96 GB) + 64 GB host RAM — vs vLLM NVFP4/FP8 and vs Qwen3.8-27B

new activity about 1 month ago

turboderp/Qwen3.8-Flash-Next-exl3:Does this support ngram nvme offloading for people with 32GB system RAM?

new activity about 1 month ago

primitive-ai/Qwen3.8-Flash-Next-mixed-NVFP4-FP8:Error when using --moe-backend marlin per the 09-03 suggestion

View all activity

Organizations

None yet

timbuksu 's datasets

None public yet