Repo

gpt-oss-120b-p104-pascal

@sergey-automationby Serhii Trykhlieb · Independent

0

Running GPT-OSS-120B Q4_K_M on 10x NVIDIA P104-100 8GB over PCIe Gen1 x1 using llama.cpp CUDA multi-GPU layer split.

See what other members are building and what each project is looking for.