Quadro RTX 4000

3 records across 2 models (quants: Q4_0, Q5_K_M-dyn).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
Quadro RTX 4000clef-flash Q5_K_M-dynllama.cpp (CUDA)1100–––16384–community–source
Quadro RTX 4000llama 7B Q4_0llama.cpp (CUDA)67.621662.8––tg1282025-11-21community–source
Quadro RTX 4000llama 7B Q4_0llama.cpp (CUDA)65.621536.89––tg1282025-11-21community–source

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

← all hardware