Falcon-H1-7B

10 records across 2 hardware.

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
RTX PRO 6000Falcon-H1-7B 7BQ4_K_Mllama.cpp (CUDA)1417.1––––2026-08community–source
RTX PRO 6000Falcon-H1-7B 7BQ8_0llama.cpp (CUDA)1318.3––––2026-08community–source
RTX PRO 6000Falcon-H1-7B 7BBF16llama.cpp (CUDA)1188.2––––2026-08community–source
RTX PRO 6000Falcon-H1-7B 7BQ4_K_Mllama.cpp (CUDA)1067.9––––2026-08community–source
RTX PRO 6000Falcon-H1-7B 7BQ8_0llama.cpp (CUDA)963.3––––2026-08community–source
RTX PRO 6000Falcon-H1-7B 7BBF16llama.cpp (CUDA)771.5––––2026-08community–source
GB10Falcon-H1-7B 7BQ4_K_Mllama.cpp (CUDA)273.1––––2026-08community–source
GB10Falcon-H1-7B 7BBF16llama.cpp (CUDA)199.0––––2026-08community–source
GB10Falcon-H1-7B 7BQ4_K_Mllama.cpp (CUDA)187.7––––2026-08community–source
GB10Falcon-H1-7B 7BBF16llama.cpp (CUDA)80.0––––2026-08community–source

← all models