0xSero
@0xSero
permanent abundance
가입 December 2020
1.7K 팔로잉 중 71.8K 팬
GPU poor rejoice!
You will be able to run Qwen3.8-Next-Flash on a single 24-32 GB GPU + 64GB ddr4/ddr5 + 100GB NVMe/SSD
RTX 3090:
- 2000 / 2800 tok/s prefill
- 64 tok/s decode c1
- 210k fp8 cache
Intel Arc B70:
- 800 / 1200 prefill tok/s
- 35 decode tok/s
- 270k fp8 cache
더 보기
