Welp-35B-A3B

6 records across 1 hardware.

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
RTX 4080 SUPERWelp-35B-A3B UD-IQ3_XXSllama.cpp (CUDA)165–––2621442026-10-08community–source
RTX 4080 SUPERWelp-35B-A3B 13.21 GBllama.cpp (CUDA)164–––2621442026-10-08community–source
RTX 4080 SUPERWelp-35B-A3B 13.21 GBllama.cpp (CUDA)107–––2621442026-10-08community–source
RTX 4080 SUPERWelp-35B-A3B 13.21 GBllama.cpp (CUDA)–5111––2621442026-10-08community–source
RTX 4080 SUPERWelp-35B-A3B UD-IQ3_XXSllama.cpp (CUDA)–5165––2621442026-10-08community–source
RTX 4080 SUPERWelp-35B-A3B 13.21 GBllama.cpp (CUDA)–2043––2621442026-10-08community–source

← all models