Studied Engineering and ICT at the Norwegian University of Science and Technology.
Pinned Loading
-
-
QwFN-hybrid
QwFN-hybrid PublicQwen3.8-Flash-Next (125B MoE) on one 16 GB GPU + 32 GB RAM: up to 1.9x faster decoding than llama.cpp, parity-gated against it
C++ 1
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
