DiggTop

Llama-3.2-1B-Instruct

Llama family · 1.0B params

1recorded run
699.9best tok/s
1verified
Fastest GPUs for this model (best tok/s)
  1. RTX PRO 6000 Blackwell699.9

All benchmarks Methodology

GPUModelQuantBackendCtx tok/sprompt tok/sVRAM GBSource
RTX PRO 6000 Blackwell · 96 GBLlama-3.2-1B-InstructQ8_0llama.cpp 876a4324096699.9 64851.32.1src