Laguna-M.1
Performance benchmark · measured on 27.07.2026 23:04
Benchmark-ID
run-20260728-034052-5cd3eaTimebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: NVFP4
Generation5,93tok/s
Prefill57,55tok/s
Time to First Token151.267,00ms
Total duration1.200,00s
Concurrency10parallel
