IBM Z Neural Network Processing Assist (NNPA)

16 records across 1 models (quants: Q8_0).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)12.53––––2026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)9.02––––2026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)5.39–––10242026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)4.61–––10242026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)3.79–––20482026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)3.34–––20482026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)2.32–––40962026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)2.18–––40962026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–25.81–––2026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–249.62–––2026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–22.85––10242026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–107.69––10242026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–20.41––20482026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–68.02––20482026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–16.89––40962026-10-02community–source
IBM Z Neural Network Processing Assist (NNPA)llama 1B Q8_0llama.cpp (zDNN)–40.41––40962026-10-02community–source

All rows cite their source. Provenance: community 40018 sourced 1085

← all hardware