DiggTop

Bonsai-27B

Qwen family · 28.0B params

2recorded runs
136.7best tok/s
1verified
Fastest GPUs for this model (best tok/s)
  1. RTX 5090136.7
  2. RTX 308072.9

All benchmarks Methodology

GPUModelQuantBackendCtx tok/sprompt tok/sVRAM GBSource
RTX 3080 · 10 GBBonsai-27BQ1_0llama.cpp b104723276872.9 1319.85.1src
RTX 5090 · 32 GBBonsai-27BQ1_0lmstudio unknown2048136.7 389.4src